1 Load libraries
2 Load data
3 QC for downstream analyses
4 Differential gene expression
5 Identify the number of shared significantly upregulated genes between tissue types across V.tsujii and Skogsbergia sp.
- 5.1 Determine the number of shared significantly upregulated genes between compound eyes
- 5.2 Determine the number of shared significantly upregulated genes between luminous upper lip and non-lumunous upper lip
6 DGE - GO enrichment analyses for upper lip
- 6.1 Use topGO to identify enriched biological processes in the upper lip
- 6.2 Use topGO to identify enriched molecular functions in the upper lip
7 WGCNA
8 References

Supp Material for Non-Luminous Ostracod *Skogsbergia sp.*

The R Juypter Notebook serves as a comprehensive repository encompasing most of the scripts and figures relevant to the non-bioluminescent ostracod Skogsbergia sp. analyses outlined in the publication. This notebook includes the following analyses: QC steps, Differential Gene Expression (DGE), GO enrichments, Cross-Species DGE analysis, WGCNA and conservation of BCN orthologs.

Author: Lisa Yeter Mesrop

Load libraries

#load libraries 
library(tidyverse) 
library(edgeR)
library(matrixStats)
library(DESeq2)
library(dplyr)
library(readxl)
library(data.table)
library(ggplot2)
library(WGCNA)
library(VennDiagram)
library(purrr)
library(reshape2)
library(knitr)
library(RColorBrewer)
library(pheatmap)
library(topGO)
library(ggvenn)

#always use the following WGCNA functions 
options(stringsAsFactors = FALSE);
enableWGCNAThreads();
allowWGCNAThreads(nThreads = 22)

── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

✔ ggplot2 3.3.5     ✔ purrr   1.0.1
✔ tibble  3.1.6     ✔ dplyr   1.0.2
✔ tidyr   1.1.2     ✔ stringr 1.4.0
✔ readr   1.3.1     ✔ forcats 0.5.0

── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

Warning message:
“package ‘edgeR’ was built under R version 3.6.2”
Loading required package: limma


Attaching package: ‘matrixStats’


The following object is masked from ‘package:dplyr’:

    count


Loading required package: S4Vectors

Loading required package: stats4

Loading required package: BiocGenerics

Loading required package: parallel


Attaching package: ‘BiocGenerics’


The following objects are masked from ‘package:parallel’:

    clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
    clusterExport, clusterMap, parApply, parCapply, parLapply,
    parLapplyLB, parRapply, parSapply, parSapplyLB


The following object is masked from ‘package:limma’:

    plotMA


The following objects are masked from ‘package:dplyr’:

    combine, intersect, setdiff, union


The following objects are masked from ‘package:stats’:

    IQR, mad, sd, var, xtabs


The following objects are masked from ‘package:base’:

    anyDuplicated, append, as.data.frame, basename, cbind, colnames,
    dirname, do.call, duplicated, eval, evalq, Filter, Find, get, grep,
    grepl, intersect, is.unsorted, lapply, Map, mapply, match, mget,
    order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
    rbind, Reduce, rownames, sapply, setdiff, sort, table, tapply,
    union, unique, unsplit, which, which.max, which.min


Attaching package: ‘S4Vectors’


The following objects are masked from ‘package:dplyr’:

    first, rename


The following object is masked from ‘package:tidyr’:

    expand


The following object is masked from ‘package:base’:

    expand.grid


Loading required package: IRanges


Attaching package: ‘IRanges’


The following objects are masked from ‘package:dplyr’:

    collapse, desc, slice


The following object is masked from ‘package:purrr’:

    reduce


Loading required package: GenomicRanges

Loading required package: GenomeInfoDb

Loading required package: SummarizedExperiment

Loading required package: Biobase

Welcome to Bioconductor

    Vignettes contain introductory material; view with
    'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.


Attaching package: ‘Biobase’


The following objects are masked from ‘package:matrixStats’:

    anyMissing, rowMedians


Loading required package: DelayedArray

Loading required package: BiocParallel


Attaching package: ‘DelayedArray’


The following objects are masked from ‘package:matrixStats’:

    colMaxs, colMins, colRanges, rowMaxs, rowMins, rowRanges


The following object is masked from ‘package:purrr’:

    simplify


The following objects are masked from ‘package:base’:

    aperm, apply, rowsum


Attaching package: ‘data.table’


The following object is masked from ‘package:SummarizedExperiment’:

    shift


The following object is masked from ‘package:GenomicRanges’:

    shift


The following object is masked from ‘package:IRanges’:

    shift


The following objects are masked from ‘package:S4Vectors’:

    first, second


The following objects are masked from ‘package:dplyr’:

    between, first, last


The following object is masked from ‘package:purrr’:

    transpose


Loading required package: dynamicTreeCut

Loading required package: fastcluster


Attaching package: ‘fastcluster’


The following object is masked from ‘package:stats’:

    hclust


Attaching package: ‘WGCNA’


The following object is masked from ‘package:IRanges’:

    cor


The following object is masked from ‘package:S4Vectors’:

    cor


The following object is masked from ‘package:stats’:

    cor


Loading required package: grid

Loading required package: futile.logger


Attaching package: ‘reshape2’


The following objects are masked from ‘package:data.table’:

    dcast, melt


The following object is masked from ‘package:tidyr’:

    smiths


Loading required package: graph


Attaching package: ‘graph’


The following object is masked from ‘package:stringr’:

    boundary


Loading required package: GO.db

Loading required package: AnnotationDbi


Attaching package: ‘AnnotationDbi’


The following object is masked from ‘package:dplyr’:

    select


Loading required package: SparseM


Attaching package: ‘SparseM’


The following object is masked from ‘package:base’:

    backsolve


groupGOTerms: 	GOBPTerm, GOMFTerm, GOCCTerm environments built.


Attaching package: ‘topGO’


The following object is masked from ‘package:grid’:

    depth


The following object is masked from ‘package:IRanges’:

    members

Allowing parallel execution with up to 39 working processes.
Allowing multi-threading with up to 22 threads.

Load data

Import Skogsbergia sp. gene expression matrix which consists of three tissue types - upper lip, compound eye and gut - with five biological replicates for each tissue. Generate the sample name sheet (meta sheet) for downstream DESeq2 analyses. Read in the annotation file for Skogsbergia sp. generated by Trinotate.

#read in gene expression matrix 
skogs_counts <- read.delim("skogs_fasta90_isoform_combined.tab", header = TRUE, sep = "\t", quote = "")

head(skogs_counts)

#fix the column names 
row.names(skogs_counts) <-skogs_counts$X

head(skogs_counts)

#remove the column X and extra X.1 
skogs_counts$X.1 <- NULL 
skogs_counts$X <- NULL

head(skogs_counts)

meta <- data.frame(row.names = colnames(skogs_counts))

head(meta)

sample_name = c("Upper_lip", "Eye", "Gut", "Upper_lip", "Eye", "Gut", "Upper_lip", "Eye", "Gut", "Upper_lip", "Eye", "Gut","Upper_lip", "Eye", "Gut")

meta$sample_name <- sample_name

meta$names <- rownames(meta)

rownames(meta) <- NULL

meta

QC for downstream analyses

#import count table, meta and sample_name into a DESeq2 object
dds_count_table <- DESeqDataSetFromMatrix(countData = skogs_counts, colData = meta, design = ~sample_name)

Warning message in DESeqDataSet(se, design = design, ignoreRank):
“some variables in design formula are characters, converting to factors”

nrow(counts(dds_count_table))

#the number of prefiltered counts for each sample
colSums(assay(dds_count_table))

Barplot of counts for all samples

The counts of raw reads were examined using a bar plot.

#visualize prefiltered raw counts in a barplot  

librarySizes <- colSums(assay(dds_count_table))

par(mar=c(10,5,2,2))  
barplot(librarySizes, 
        las=2, 
        cex.names=.5,
        main="Barplot of raw count distributions of samples")

Visualize transformed expression matrix with hierarchical clustering and PCA

# run DESeq2 function and normalization  
dds_raw_counts <- DESeq(dds_count_table, betaPrior = FALSE, parallel = TRUE) 
# Perform a variance-stabilizing transformation
vsd_raw_counts <- varianceStabilizingTransformation(dds_raw_counts)

estimating size factors

estimating dispersions

gene-wise dispersion estimates: 38 workers

mean-dispersion relationship

final dispersion estimates, fitting model and testing: 38 workers

sampleDists_raw_counts <- dist(t(assay(vsd_raw_counts)))

#plot the heatmap
sampleDists_raw_counts_Matrix <- as.matrix(sampleDists_raw_counts)
rownames(sampleDists_raw_counts_Matrix) <- paste(colData(dds_raw_counts)$sample_name) 
colnames(sampleDists_raw_counts_Matrix) <- colData(dds_raw_counts)$names
colors <- colorRampPalette( rev(brewer.pal(9, "Blues")) )(255)
pheatmap(sampleDists_raw_counts_Matrix,
          clustering_distance_rows=sampleDists_raw_counts,
         clustering_distance_cols=sampleDists_raw_counts,
         col=colors)

#plot the PCA
pcaData_raw_counts <- plotPCA(vsd_raw_counts, intgroup="sample_name", returnData=TRUE)
percentVar_raw_counts <- round(100 * attr(pcaData_raw_counts, "percentVar"))
ggplot(pcaData_raw_counts, aes(PC1, PC2, color=sample_name, shape=sample_name)) +
  geom_point(size=5) +
  xlab(paste0("PC1: ",percentVar_raw_counts[1],"% variance")) +
  ylab(paste0("PC2: ",percentVar_raw_counts[2],"% variance")) + 
   geom_point(size=5) +
theme(panel.grid.major = element_line(colour = "gray97",  size = 1), panel.grid.minor = element_line(linetype = "dotted"), panel.background = element_rect(fill = NA), 
   legend.key = element_rect(fill = "gray100")) + theme(axis.line = element_line(size = 0.5,linetype = "solid")) + 
  theme(panel.border = element_rect(colour = "black", fill=NA, size=1)) +
coord_fixed() +
scale_color_manual(values = c('#F2C93D','#C97D97','#F1AFB4'))+theme(
    legend.title = element_text(size = 16),
    legend.text = element_text(size = 14),  
    axis.title.x = element_text(size = 16),  
    axis.title.y = element_text(size = 16),  
    axis.text = element_text(size = 12)  
  )

options(repr.plot.width=8, repr.plot.height=6, repr.plot.res = 150)

Import the annotation for Skogsbergia sp. transcriptome

#read in the Trinotate sheet for Skogsbergia sp. 

Trinotate_lym_subset_skogs <- read.csv(file = "Trinotate_lym_subset_Skogsbergia_cdhit90_longestisoform.csv")

Prep expression matrix for WGCNA

As a preliminary quality control (QC) measure for WGCNA analysis, the overall similarity between samples and transcripts with low counts was assessed, as these counts often introduce noise in co-expression analyses. A filter was applied to the expression matrix, removing transcripts with fewer than 5 counts in more than 5 samples, given that some sample types included a minimum of 5 biological replicates. The QC analyses utilized functions from the DESeq2 package (Love et al., 2014). The WGCNA analysis is used for construction of co-expression networks for Skogsbergia sp. and conservation of BCN orthologs in the networks of the non-luminous Skogsbergia sp. in Section 7.

#import count table into a DESeq2 
dds_count_table_wgcna <- DESeqDataSetFromMatrix(countData = skogs_counts, colData = meta, design = ~sample_name)

Warning message in DESeqDataSet(se, design = design, ignoreRank):
“some variables in design formula are characters, converting to factors”

#filter the count table 
dds_merged_table_prefiltered_wgcna <- dds_count_table_wgcna[rowSums(counts(dds_count_table_wgcna) >= 5) >=5,];
nrow(dds_merged_table_prefiltered_wgcna

# run DESeq2 function and normalization  
dds_prefiltered_wgcna <- DESeq(dds_merged_table_prefiltered_wgcna, betaPrior = FALSE, parallel = TRUE) ;#make sure that these are default parameters, betaPrior and parallel
# Perform a variance-stabilizing transformation
vsd_prefiltered_wgcna <- varianceStabilizingTransformation(dds_prefiltered_wgcna)

estimating size factors

estimating dispersions

gene-wise dispersion estimates: 38 workers

mean-dispersion relationship

final dispersion estimates, fitting model and testing: 38 workers

#transpose the matrix
sampleDists_wgcna <- dist(t(assay(vsd_prefiltered_wgcna)))

#plot the heatmap
sampleDistMatrix_wgcna <- as.matrix(sampleDists_wgcna)
rownames(sampleDistMatrix_wgcna) <- paste(colData(dds_merged_table_prefiltered_wgcna)$sample_name) 
colnames(sampleDistMatrix_wgcna) <- colData(dds_merged_table_prefiltered_wgcna)$names
colors <- colorRampPalette( rev(brewer.pal(9, "Blues")) )(255)
pheatmap(sampleDistMatrix_wgcna,
          clustering_distance_rows=sampleDists_wgcna,
         clustering_distance_cols=sampleDists_wgcna,
         col=colors)

#plot the PCA 

pcaData_prefiltered_wgcna <- plotPCA(vsd_prefiltered_wgcna, intgroup="sample_name", returnData=TRUE)
percentVar_prefiltered_wgcna <- round(100 * attr(pcaData_prefiltered_wgcna, "percentVar"))
ggplot(pcaData_prefiltered_wgcna, aes(PC1, PC2, color=sample_name, shape=sample_name)) +
  geom_point(size=5) +
theme(panel.grid.major = element_line(colour = "gray97",  size = 1), panel.grid.minor = element_line(linetype = "dotted"), panel.background = element_rect(fill = NA), 
   legend.key = element_rect(fill = "gray100")) + theme(axis.line = element_line(size = 0.5,linetype = "solid")) + 
  theme(panel.border = element_rect(colour = "black", fill=NA, size=1)) +
scale_color_manual(values = c('#C24C3D','#8E3DC2','#E69F00'))+
  xlab(paste0("PC1: ",percentVar_raw_counts[1],"% variance")) +
  ylab(paste0("PC2: ",percentVar_raw_counts[2],"% variance")) + 
  coord_fixed()

Differential gene expression

Differential gene expression analysis was carried out in DESeq2 (Love et al., 2014). For Skogsbergia sp. , we determined differentially upregulated genes in three tissue types - upper lip, compound eye and gut - using five biological replicates for each tissue. DESeq2 was employed using a p-value < 0.05 and FC > 1.5 for the significance of differentially expressed genes using the Benjamini-Hochberg method to account for false discovery rate (FDR). Pairwise comparisons were done across tissue types (i.e., upper lip to compound eye, upper lip to gut, gut to compound eye). To identify tissue-specific differential expression (i.e. significantly upregulated genes that are uniquely expressed), each tissue was compared to the other two. For example, the expression in the upper lip was determined by comparing it to both the compound eye and the gut tissues. For each pairwise comparison, the reference tissue was specified to determine the significantly upregulated genes in each tissue type (i.e., positive vs negative logfold change).

dds_count_table

class: DESeqDataSet 
dim: 81092 15 
metadata(1): version
assays(1): counts
rownames(81092): TRINITY_DN0_c0_g1_i2 TRINITY_DN0_c0_g3_i1 ...
  TRINITY_DN99_c4_g1_i1 TRINITY_DN9_c0_g1_i1
rowData names(0):
colnames(15): Sk.10A_fasta90_isoform.counts.tab
  Sk.10B_fasta90_isoform.counts.tab ...
  Sk.9B_fasta90_isoform..counts.tab Sk.9C_fasta90_isoform.counts.tab
colData names(2): sample_name names

#run DESeq2 analysis
dds_DE <- DESeq(dds_count_table)

estimating size factors

estimating dispersions

gene-wise dispersion estimates

mean-dispersion relationship

final dispersion estimates

fitting model and testing

DGE - Upper Lip vs Compound Eye

#set eye as a reference tissue 
dds_DE$sample_name <- relevel(dds_DE$sample_name, ref= "Eye")

#rerun DESeq command after reference is specified 
dds_DE <- DESeq(dds_DE)

using pre-existing size factors

estimating dispersions

found already estimated dispersions, replacing these

gene-wise dispersion estimates

mean-dispersion relationship

final dispersion estimates

fitting model and testing

#define contrasts, extract results table, and shrink the log2 fold changes

res_tableOE_unshrunken_UpperlipVs_Eye <- results(dds_DE, contrast= c("sample_name", "Upper_lip", "Eye") , alpha = 0.05)


res_tableOE_UpperlipVs_Eye <- lfcShrink(dds_DE, contrast= c("sample_name", "Upper_lip", "Eye"), res = res_tableOE_unshrunken_UpperlipVs_Eye)

using 'normal' for LFC shrinkage, the Normal prior from Love et al (2014).

Note that type='apeglm' and type='ashr' have shown to have less bias than type='normal'.
See ?lfcShrink for more details on shrinkage type, and the DESeq2 vignette.
Reference: https://doi.org/10.1093/bioinformatics/bty895

mcols(res_tableOE_UpperlipVs_Eye, use.names=T)

DataFrame with 6 rows and 2 columns
                       type
                <character>
baseMean       intermediate
log2FoldChange      results
lfcSE               results
stat                results
pvalue              results
padj                results
                                                        description
                                                        <character>
baseMean                  mean of normalized counts for all samples
log2FoldChange log2 fold change (MAP): sample_name Upper_lip vs Eye
lfcSE                  standard error: sample_name Upper_lip vs Eye
stat                   Wald statistic: sample name Upper lip vs Eye
pvalue              Wald test p-value: sample name Upper lip vs Eye
padj                                           BH adjusted p-values

# set thresholds
# lfc.cutoff value of 0.58 translates to a 1.5 log2 fold change 
# padj.cutoff value of 0.05 

padj.cutoff <- 0.05
lfc.cutoff <- 0.58

res_tableOE_UpperlipVs_Eye_tb <- res_tableOE_UpperlipVs_Eye %>%
  data.frame() %>%
  rownames_to_column(var="gene") %>% 
  as_tibble()

#determine all differentially expressed genes 
sigOE_UpperlipVs_Eye <- res_tableOE_UpperlipVs_Eye_tb %>%
        filter(padj < padj.cutoff & abs(log2FoldChange) > lfc.cutoff)

colnames(sigOE_UpperlipVs_Eye)[1]<- "transcript_id"

head(sigOE_UpperlipVs_Eye)

#extract all genes that are significantly upregulated in the Upper Lip (positive log2 fold change)
Upperlip_Vs_eye_sigOE_UPREGULATED_logfold <- sigOE_UpperlipVs_Eye %>%
        filter(padj < padj.cutoff & log2FoldChange > lfc.cutoff)

colnames(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold)[1]<- "transcript_id"

#add the annotation  
Upperlip_Vs_eye_sigOE_UPREGULATED_logfold_annot <- setDT(Trinotate_lym_subset_skogs, key = 'transcript_id')[J(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold)]

#genes that are significantly upregulated in the Upper Lip (positive log2 fold change)
head(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold_annot)

#extract all genes that are significantly upregulated in the Compound Eye (negative log2fold change) but that are downregulated in the upper lip.

Upperlip_Vs_eye_sigOE_DOWNREGULATED_logfold <- sigOE_UpperlipVs_Eye %>%
        filter(padj < padj.cutoff & log2FoldChange < lfc.cutoff)

#save these two dataframes for downstream analysis in Section 4.4 

#genes that are significantly upregulated in the Upper Lip (positive log2 fold change)
head(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold)

#genes that significantly upregulated in the Compound Eye (negative log2fold change) but that are downregulated in the upper lip.
head(Upperlip_Vs_eye_sigOE_DOWNREGULATED_logfold)

DGE - Gut vs Compound Eye

#define contrasts, extract results table, and shrink the log2 fold changes

res_tableOE_unshrunken_GutVsEye <- results(dds_DE, contrast= c("sample_name", "Gut", "Eye") , alpha = 0.05)


res_tableOE_GutVsEye <- lfcShrink(dds_DE, contrast= c("sample_name", "Gut", "Eye"), res = res_tableOE_unshrunken_GutVsEye)

using 'normal' for LFC shrinkage, the Normal prior from Love et al (2014).

Note that type='apeglm' and type='ashr' have shown to have less bias than type='normal'.
See ?lfcShrink for more details on shrinkage type, and the DESeq2 vignette.
Reference: https://doi.org/10.1093/bioinformatics/bty895

mcols(res_tableOE_GutVsEye, use.names=T)

DataFrame with 6 rows and 2 columns
                       type                                    description
                <character>                                    <character>
baseMean       intermediate      mean of normalized counts for all samples
log2FoldChange      results log2 fold change (MAP): sample_name Gut vs Eye
lfcSE               results         standard error: sample_name Gut vs Eye
stat                results         Wald statistic: sample name Gut vs Eye
pvalue              results      Wald test p-value: sample name Gut vs Eye
padj                results                           BH adjusted p-values

res_tableOE_tb_GutVsEye <- res_tableOE_GutVsEye %>%
  data.frame() %>%
  rownames_to_column(var="gene") %>% 
  as_tibble()

#determine all differentially expressed genes 
sigOE_GutVsEye <- res_tableOE_tb_GutVsEye %>%
        filter(padj < padj.cutoff & abs(log2FoldChange) > lfc.cutoff)

colnames(sigOE_GutVsEye)[1]<- "transcript_id"

#extract all genes that are significantly upregulated in the gut (positive log2 fold change)
GutVsEye_sigOE_UPREGULATED_logfold <- sigOE_GutVsEye %>%
        filter(padj < padj.cutoff & log2FoldChange > lfc.cutoff)

#match the nodes 
GutVsEye_sigOE_UPREGULATED_logfold_annot <- setDT(Trinotate_lym_subset_skogs, key = 'transcript_id')[J(GutVsEye_sigOE_UPREGULATED_logfold)]

#genes that are significantly upregulated in the gut (positive log2 fold change)
head(GutVsEye_sigOE_UPREGULATED_logfold_annot)

#extract all genes that are significantly upregulated in the Compound Eye (negative log2fold change) but that are downregulated in the gut.  

#extract all genes that are significantly upregulated in the Compound Eye
GutVsEye_sigOE_DOWNREGULATED_logfold <- sigOE_GutVsEye %>%
        filter(padj < padj.cutoff & log2FoldChange < lfc.cutoff)

#save these two dataframes for downstream analysis

#genes that are significantly upregulated in the Gut (positive log2 fold change)
head(GutVsEye_sigOE_UPREGULATED_logfold)

#genes that are significantly upregulated in the Compound Eye ((negative log2fold change) but that are downregulated in the gut 
head(GutVsEye_sigOE_DOWNREGULATED_logfold)

DGE - Upper Lip vs Gut

#now set gut as a reference tissue 
dds_DE$sample_name <- relevel(dds_DE$sample_name, ref= "Gut")

#rerun DESeq 
dds_DE <- DESeq(dds_DE)

using pre-existing size factors

estimating dispersions

found already estimated dispersions, replacing these

gene-wise dispersion estimates

mean-dispersion relationship

final dispersion estimates

fitting model and testing

#define contrasts, extract results table, and shrink the log2 fold changes

res_tableOE_unshrunken_UpperLipVsGut <- results(dds_DE, contrast= c("sample_name", "Upper_lip", "Gut") , alpha = 0.05)


res_tableOE_UpperLipVsGut <- lfcShrink(dds_DE, contrast= c("sample_name", "Upper_lip", "Gut"), res = res_tableOE_unshrunken_UpperLipVsGut)

using 'normal' for LFC shrinkage, the Normal prior from Love et al (2014).

Note that type='apeglm' and type='ashr' have shown to have less bias than type='normal'.
See ?lfcShrink for more details on shrinkage type, and the DESeq2 vignette.
Reference: https://doi.org/10.1093/bioinformatics/bty895

mcols(res_tableOE_UpperLipVsGut, use.names=T)

DataFrame with 6 rows and 2 columns
                       type
                <character>
baseMean       intermediate
log2FoldChange      results
lfcSE               results
stat                results
pvalue              results
padj                results
                                                        description
                                                        <character>
baseMean                  mean of normalized counts for all samples
log2FoldChange log2 fold change (MAP): sample_name Upper_lip vs Gut
lfcSE                  standard error: sample_name Upper_lip vs Gut
stat                   Wald statistic: sample name Upper lip vs Gut
pvalue              Wald test p-value: sample name Upper lip vs Gut
padj                                           BH adjusted p-values

res_tableOE_tb_UpperLipVsGut <- res_tableOE_UpperLipVsGut %>%
  data.frame() %>%
  rownames_to_column(var="gene") %>% 
  as_tibble()

#determine all differentially expressed genes 
sigOE_UpperLipVsGut <- res_tableOE_tb_UpperLipVsGut %>%
        filter(padj < padj.cutoff & abs(log2FoldChange) > lfc.cutoff)

#extract all genes that are significantly upregulated in the upper lip (positive log2 fold change)
UpperLipVsGut_sigOE_UPREGULATED_logfold <- sigOE_UpperLipVsGut %>%
        filter(padj < padj.cutoff & log2FoldChange > lfc.cutoff)

#genes that are significantly upregulated in the upper lip (positive log2 fold change)
head(UpperLipVsGut_sigOE_UPREGULATED_logfold )

#extract all genes that are significantly upregulated in the Gut (negative log2fold change)
UpperLipVsGut_sigOE_DOWNREGULATED_logfold <- sigOE_UpperLipVsGut %>%
        filter(padj < padj.cutoff & log2FoldChange < lfc.cutoff)

#extract all genes that are significantly upregulated in the Gut (negative log2fold change) but that are downregulated in the Upper Lip.  
head(UpperLipVsGut_sigOE_DOWNREGULATED_logfold)

#save these two dataframes for downstream analysis

#genes that are significantly upregulated in the upper lip (positive log2 fold change)
head(UpperLipVsGut_sigOE_UPREGULATED_logfold)

#genes that are significantly upregulated in the gut (negative log2fold change) but that are downregulated in the Upper Lip  
head(UpperLipVsGut_sigOE_DOWNREGULATED_logfold)

Determine tissue-specific expression

To identify tissue-specific differential expression (i.e., significantly upregulated genes that are uniquely expressed), each tissue was compared to the other two and tissue-specific genes were extracted from the intersection of the Venn diagram (in Section 4.4.4). For example, the expression in the upper lip was determined by comparing it to both the compound eye and gut tissues.

Upper lip

#create a dataframe with all significantly upregulated genes of the upper lip
#merge dataframes that have significantly upregulated genes of the  upper lip from pairwise comparisons - Upper Lip vs Gut and Upper Lip vs Eye

head(UpperLipVsGut_sigOE_UPREGULATED_logfold)

head(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold)

colnames(UpperLipVsGut_sigOE_UPREGULATED_logfold)[1]<- "gene"

colnames(Upperlip_Vs_eye_sigOE_UPREGULATED_logfold)[1]<- "gene"

#merge
merged_upper_lips_df <- rbind(
  UpperLipVsGut_sigOE_UPREGULATED_logfold,
  Upperlip_Vs_eye_sigOE_UPREGULATED_logfold
)

head(merged_upper_lips_df)

#the same gene can be found in both Upper Lip vs Gut and Upper Lip vs Eye. Remove gene duplicates while retaining one duplicate. 
merged_upper_lips_unique <- merged_upper_lips_df[!duplicated(merged_upper_lips_df$gene), ]

head(merged_upper_lips_unique)

Compound eye

#create a dataframe with all significantly upregulated genes of the compound eye 
#merge dataframes that have significantly upregulated genes of the compound eye from  pairwise comparisons - Upper Lip vs Compound Eye and Gut vs Compound Eye 

#genes that significantly upregulated in the Compound Eye
head(Upperlip_Vs_eye_sigOE_DOWNREGULATED_logfold)

#genes that are significantly upregulated in the Compound Eye
head(GutVsEye_sigOE_DOWNREGULATED_logfold)

colnames(Upperlip_Vs_eye_sigOE_DOWNREGULATED_logfold)[1]<- "gene"

colnames(GutVsEye_sigOE_DOWNREGULATED_logfold)[1]<- "gene"

#merged eye
merged_Eye_df <- rbind(Upperlip_Vs_eye_sigOE_DOWNREGULATED_logfold , GutVsEye_sigOE_DOWNREGULATED_logfold)

head(merged_Eye_df)

#the same gene can be found in both Upper Lip vs Compound Eye and Gut vs Compound Eye. Remove gene duplicates while retaining one duplicate. 
merged_Eye_unique <-merged_Eye_df[!duplicated(merged_Eye_df$gene), ]

head(merged_Eye_unique)

Gut

#create a dataframe with all significantly upregulated genes of the gut  
#merge dataframes that have significantly upregulated genes of the gut from pairwise comparisons - Gut vs Eye and Upper lip vs Gut

#genes that are significantly upregulated in the Gut
head(GutVsEye_sigOE_UPREGULATED_logfold)

#genes that are significantly upregulated in the gut 
head(UpperLipVsGut_sigOE_DOWNREGULATED_logfold)

colnames(GutVsEye_sigOE_UPREGULATED_logfold)[1]<- "gene"

colnames(UpperLipVsGut_sigOE_DOWNREGULATED_logfold)[1]<- "gene"

#merge
merged_Gut_df <- rbind(GutVsEye_sigOE_UPREGULATED_logfold , UpperLipVsGut_sigOE_DOWNREGULATED_logfold)

head(merged_Gut_df)

#the same gene can be found in both Gut vs Eye and Upper lip vs Gut. Remove gene duplicates while retaining one duplicate.
merged_Gut_unique <-merged_Gut_df[!duplicated(merged_Gut_df$gene), ]

head(merged_Gut_unique)

Venn Diagram - Extract tissue-specific genes

#generate a venn diagram to visualize shared significantly upregulated genes across tissue types and extract the genes that are unique to each tissue type. 
unique_venn_list <- list(
  Upper_Lip = merged_upper_lips_unique$gene  , 
  Gut = merged_Gut_unique$gene,
  Compound_Eye = merged_Eye_unique$gene
)

ggvenn_unique <- ggvenn(
  unique_venn_list, 
  fill_color = c('#F1AFB4','#C97D97', '#F2C93D'),
  stroke_size = .7, set_name_size = 6, text_size = 5
)

ggvenn_unique

# Open a PDF device
pdf("Non_Luminous_DGE.pdf", width = 8, height = 6)


ggvenn_unique 

dev.off()

#prep dataframes for extraction
Upper_Lip <- as.data.frame(merged_upper_lips_unique$gene)
colnames(Upper_Lip)[1]<- "gene"
Gut <- as.data.frame(merged_Gut_unique$gene)
colnames(Gut)[1]<- "gene"
Compound_eye <- as.data.frame(merged_Eye_unique$gene)
colnames(Compound_eye)[1]<- "gene"

# compare and extract unique genes for each tissue type
unique_genes_upper_lip <- anti_join(Upper_Lip, Gut, by = "gene") %>%
  anti_join(Compound_eye, by = "gene")

unique_genes_gut <- anti_join(Gut, Upper_Lip, by = "gene") %>%
  anti_join(Compound_eye, by = "gene")

unique_genes_compound_eye <- anti_join(Compound_eye, Upper_Lip, by = "gene") %>%
  anti_join(Gut, by = "gene")

nrow(unique_genes_upper_lip)

nrow(unique_genes_gut)

nrow(unique_genes_compound_eye)

#add the annotations back to the unique genes in each tissue type by subsetting

unique_genes_upper_lip_info  <- merged_upper_lips_unique %>%
  filter(gene %in% unique_genes_upper_lip$gene)

nrow(unique_genes_upper_lip_info)

unique_genes_eye_info  <- merged_Eye_unique %>%
  filter(gene %in% unique_genes_compound_eye$gene)

nrow(unique_genes_eye_info)

unique_genes_gut_info  <- merged_Gut_unique %>%
  filter(gene %in% unique_genes_gut$gene)

nrow(unique_genes_gut_info)

#add annotations back for upper lip
colnames(unique_genes_upper_lip_info)[1]<- "transcript_id"
unique_genes_upper_lip_info_annot <- left_join(unique_genes_upper_lip_info,Trinotate_lym_subset_skogs,by="transcript_id")

#write.csv(unique_genes_upper_lip_info_annot, file = "df_Skogs_sigfig_upreg_unique_Upper_Lip.csv")

#add annotations back for eyes 
colnames(unique_genes_eye_info)[1]<- "transcript_id"
unique_genes_eye_info_annot <- left_join(unique_genes_eye_info,Trinotate_lym_subset_skogs,by="transcript_id")

#write.csv(unique_genes_eye_info_annot, file = "df_Skogs_sigfig_upreg_unique_comEye.csv")

#add annotations back for gut 
colnames(unique_genes_gut_info)[1] <- "transcript_id"
unique_genes_gut_info_annot <- left_join(unique_genes_gut_info,Trinotate_lym_subset_skogs,by="transcript_id")

#write.csv(unique_genes_gut_info_annot, file = "df_Skogs_sigfig_upreg_unique_Gut.csv")

Identify the number of shared significantly upregulated genes between tissue types across V.tsujii and Skogsbergia sp.

Compared the number of significantly upregulated genes (expressed uniquely) between upper lips and compound eyes of luminous and non-luminous ostracods.

Determine the number of shared significantly upregulated genes between compound eyes

Import

#import V.tsujii compound eyes 
vtsujii_eye <- read.csv("df_Vtsujii_sigfig_upreg_unique_comEye.csv", header = TRUE, row.names=1,
                  stringsAsFactors = FALSE)

#change column name 
colnames(vtsujii_eye)[1]<- "gene"

vargulatsujii_v_skogsbergia_orthologs_factor <- read.csv("Vargula_tsujii_cdhit_95.fasta.transdecoder__v__Skogsbergia_sp.csv")

head(vargulatsujii_v_skogsbergia_orthologs_factor)

Determine the orthogroups that contain V.tsujii significantly upregulated compound eye genes

#find the orthogroups that have V.tsujii DE compound eye transcripts 
vtsujii_DE_eye <- subset(vtsujii_eye, select = "gene")

head(vtsujii_DE_eye)

# run the function and change the column names accordingly

check_and_subset <- function(df1, df2) {
  matched_rows_list <- list()
  for (i in 1:nrow(df1)) {
    char_row <- df1[i, "gene"]
    matched_rows <- df2[str_detect(df2$Vargula_tsujii_cdhit_95.fasta.transdecoder, paste0(char_row, collapse = "|")), , drop = FALSE]
    if (nrow(matched_rows) > 0) {
      matched_rows_list[[i]] <- matched_rows
    }
  }
  if (length(matched_rows_list) > 0) {
    matched_df <- bind_rows(matched_rows_list)
    return(matched_df)
  } else {
    return(NULL)
  }
}

# Use the function 
vtsujii_DE_eye_orthogroups <- check_and_subset(vtsujii_DE_eye, 
vargulatsujii_v_skogsbergia_orthologs_factor)

head(vtsujii_DE_eye_orthogroups)

vtsujii_DE_eye_orthogroups_numbers <- subset(vtsujii_DE_eye_orthogroups, select = "Orthogroup")

head(vtsujii_DE_eye_orthogroups_numbers)

vtsujii_DE_eye_orthogroups_numbers_rmdup <- vtsujii_DE_eye_orthogroups_numbers %>% distinct()

nrow(vtsujii_DE_eye_orthogroups_numbers_rmdup)

Determine the orthogroups that contain Skogsbergia sp. significantly upregulated compound eye genes

skogs_DE_eye <- subset(unique_genes_compound_eye, select = "gene")

colnames(skogs_DE_eye)[1]<- "transcript_id"

head(skogs_DE_eye)

# use this function and change the column names 

check_and_subset <- function(df1, df2) {
  matched_rows_list <- list()
  for (i in 1:nrow(df1)) {
    char_row <- df1[i, "transcript_id"]
    matched_rows <- df2[str_detect(df2$Skogsbergia_sp, paste0(char_row, collapse = "|")), , drop = FALSE]
    if (nrow(matched_rows) > 0) {
      matched_rows_list[[i]] <- matched_rows
    }
  }
  if (length(matched_rows_list) > 0) {
    matched_df <- bind_rows(matched_rows_list)
    return(matched_df)
  } else {
    return(NULL)
  }
}

# Use the function 
skogs_DE_eye_orthogroups <- check_and_subset(skogs_DE_eye, vargulatsujii_v_skogsbergia_orthologs_factor)

head(skogs_DE_eye_orthogroups)

skogs_DE_eye_orthogroups_numbers <- subset(skogs_DE_eye_orthogroups, select = "Orthogroup" )

skogs_DE_eye_orthogroups_numbers_rmdup <- skogs_DE_eye_orthogroups_numbers %>% distinct()

nrow(skogs_DE_eye_orthogroups_numbers_rmdup)

Determine the number of orthogroups with significantly upregulated compound eye genes shared between V.tsujii and Skogsbergia sp.

head(vtsujii_DE_eye_orthogroups_numbers_rmdup$Orthogroup)

head(skogs_DE_eye_orthogroups_numbers_rmdup$Orthogroup)

#convert columns to characters for the function below 

vtsujii_DE_eye_orthogroups_numbers_rmdup <- vtsujii_DE_eye_orthogroups_numbers_rmdup %>% mutate(Orthogroup = as.character(Orthogroup))

skogs_DE_eye_orthogroups_numbers_rmdup <- skogs_DE_eye_orthogroups_numbers_rmdup %>% mutate(Orthogroup = as.character(Orthogroup))

#start with the longer list first which is V.tsujii


vtsujii_skogs_orthogroups_numbers_match <- vtsujii_DE_eye_orthogroups_numbers_rmdup %>%
    mutate(match = c("no", "yes")[1 + (rowSums(
        outer(
            strsplit(Orthogroup, "\\s+"),
            strsplit(skogs_DE_eye_orthogroups_numbers_rmdup$Orthogroup, "\\s+"),
            Vectorize(function(x, y) all(x %in% y) | all(y %in% x))
        )
    ) > 0)])

head(vtsujii_skogs_orthogroups_numbers_match)

vtsujii_skogs_orthogroups_numbers_match_yes <- vtsujii_skogs_orthogroups_numbers_match %>% filter(match=="yes")

vtsujii_skogs_orthogroups_numbers_match_yes

#take the Orthogroup numbers  


vtsujii_skogs_orthogroups_numbers_match_yes_ch <- as.character(vtsujii_skogs_orthogroups_numbers_match_yes$Orthogroup)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES <-  vargulatsujii_v_skogsbergia_orthologs_factor %>% filter(Orthogroup %in% vtsujii_skogs_orthogroups_numbers_match_yes_ch)

head(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES)

Extract all V.tsujii significantly upregulated compound eye genes from orthogroups shared across both compound eyes

#now extract all transcripts 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids <- as.character(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES$Vargula_tsujii_cdhit_95.fasta.transdecoder)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist  <- unlist(strsplit(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids,","))

#remove p* 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist_removep <- vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist %>% str_replace("(.p1)", "") %>% 
str_replace("(.p2)", "")

#found out there is a space in front of certain transcripts 

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist_removep_removespace <- trimws(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist_removep)

vtsujii_eye_orthogroups_transcript_ids <- vtsujii_eye %>% filter (gene %in% vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_transcript_ids_unlist_removep_removespace)

head(vtsujii_eye_orthogroups_transcript_ids)

nrow(vtsujii_eye_orthogroups_transcript_ids )

Extract all Skogsbergia sp. significantly upregulated genes from orthogroups shared across both compound eyes

#now extract all transcripts 

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids <- as.character(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES$Skogsbergia_sp)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist  <- unlist(strsplit(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids,","))


#remove p* 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist_removep <- vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist %>% str_replace("(.p1)", "") %>% 
str_replace("(.p2)", "") 
                              

#found out there is a space in front of certain transcripts 

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist_removep_removespace <- trimws(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist_removep)

skogs_eye_orthogroups_transcript_ids <- skogs_DE_eye %>% filter (transcript_id %in% vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_EYES_skogs_transcript_ids_unlist_removep_removespace)

skogs_eye_orthogroups_transcript_ids

nrow(skogs_eye_orthogroups_transcript_ids)

Determine the number of shared significantly upregulated genes between luminous upper lip and non-lumunous upper lip

Import

#import V.tsujii upper lip 
vtsujii_bio_upper_lip <- read.csv("df_Vtsujii_sigfig_upreg_unique_BioUpperLip.csv", header = TRUE, row.names=1,
                  stringsAsFactors = FALSE)

#use the already imported sheet all orthologs from Section 5.1.1
head(vargulatsujii_v_skogsbergia_orthologs_factor)

Determine the orthogroups that contain V.tsujii significantly upregulated bioluminescent upper lip genes

vtsujii_bio_upper_lip_ids <- subset(vtsujii_bio_upper_lip, select = "transcript_id")

# make sure to change the column names

check_and_subset <- function(df1, df2) {
  matched_rows_list <- list()
  for (i in 1:nrow(df1)) {
    char_row <- df1[i, "transcript_id"]
    matched_rows <- df2[str_detect(df2$Vargula_tsujii_cdhit_95.fasta.transdecoder, paste0(char_row, collapse = "|")), , drop = FALSE]
    if (nrow(matched_rows) > 0) {
      matched_rows_list[[i]] <- matched_rows
    }
  }
  if (length(matched_rows_list) > 0) {
    matched_df <- bind_rows(matched_rows_list)
    return(matched_df)
  } else {
    return(NULL)
  }
}

# use the function 
vtsujii_bio_upper_lip_orthogroups <- check_and_subset(vtsujii_bio_upper_lip_ids, 
vargulatsujii_v_skogsbergia_orthologs_factor)

head(vtsujii_bio_upper_lip_orthogroups)

#extract all the orthogroups 
vtsujii_bio_upper_lip_orthogroups_numbers <- subset(vtsujii_bio_upper_lip_orthogroups, select = "Orthogroup")

head(vtsujii_bio_upper_lip_orthogroups_numbers)

vtsujii_bio_upper_lip_orthogroups_numbers_rmdup <- vtsujii_bio_upper_lip_orthogroups_numbers %>% distinct()

nrow(vtsujii_bio_upper_lip_orthogroups_numbers_rmdup)

Determine the orthogroups that have Skogsbergia sp. significantly upregulated upper lip genes

#significantly upregulated genes (uniquely expressed) in the upper lip from Section 4.4.4
head(unique_genes_upper_lip_info)

colnames(unique_genes_upper_lip_info)[1] <- "transcript_id"

skogs_upper_lip_ids <- subset(unique_genes_upper_lip_info, select = "transcript_id")

# use this function and change the column names 

check_and_subset <- function(df1, df2) {
  matched_rows_list <- list()
  for (i in 1:nrow(df1)) {
    char_row <- df1[i, "transcript_id"]
    matched_rows <- df2[str_detect(df2$Skogsbergia_sp, paste0(char_row, collapse = "|")), , drop = FALSE]
    if (nrow(matched_rows) > 0) {
      matched_rows_list[[i]] <- matched_rows
    }
  }
  if (length(matched_rows_list) > 0) {
    matched_df <- bind_rows(matched_rows_list)
    return(matched_df)
  } else {
    return(NULL)
  }
}

# use the function 
skogs_upper_lip_orthogroups <- check_and_subset(skogs_upper_lip_ids, vargulatsujii_v_skogsbergia_orthologs_factor)

head(skogs_upper_lip_orthogroups)

skogs_upper_lip_orthogroups_numbers <- subset(skogs_upper_lip_orthogroups, select = "Orthogroup" )

skogs_upper_lip_orthogroups_numbers_rmdup <- skogs_upper_lip_orthogroups_numbers %>% distinct()

nrow(skogs_upper_lip_orthogroups_numbers_rmdup)

Determine the number of orthogroups with significantly upregulated genes shared between luminous upper lip and non-luminous upper lip.

head(vtsujii_bio_upper_lip_orthogroups_numbers_rmdup$Orthogroup)

head(skogs_upper_lip_orthogroups_numbers_rmdup$Orthogroup)

#convert columns to characters for the function below 

vtsujii_bio_upper_lip_orthogroups_numbers_rmdup_chr <- vtsujii_bio_upper_lip_orthogroups_numbers_rmdup %>% mutate(Orthogroup = as.character(Orthogroup))

skogs_upper_lip_orthogroups_numbers_rmdup_chr <- skogs_upper_lip_orthogroups_numbers_rmdup %>% mutate(Orthogroup = as.character(Orthogroup))

#start with the longer list first which is V.tsujii
vtsujii_skogs_upper_lips_orthogroups_numbers_match <- vtsujii_bio_upper_lip_orthogroups_numbers_rmdup_chr %>%
    mutate(match = c("no", "yes")[1 + (rowSums(
        outer(
            strsplit(Orthogroup, "\\s+"),
            strsplit(skogs_upper_lip_orthogroups_numbers_rmdup_chr$Orthogroup, "\\s+"),
            Vectorize(function(x, y) all(x %in% y) | all(y %in% x))
        )
    ) > 0)])

head(vtsujii_skogs_upper_lips_orthogroups_numbers_match)

vtsujii_skogs_upper_lips_orthogroups_numbers_match_yes <- vtsujii_skogs_upper_lips_orthogroups_numbers_match %>% filter(match=="yes")

vtsujii_skogs_upper_lips_orthogroups_numbers_match_yes

#take the Orthogroup numbers  
vtsujii_skogs_upper_lips_orthogroups_numbers_match_yes_ch <- as.character(vtsujii_skogs_upper_lips_orthogroups_numbers_match_yes$Orthogroup)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_UPPER_LIPS <-  vargulatsujii_v_skogsbergia_orthologs_factor %>% filter(Orthogroup %in% vtsujii_skogs_upper_lips_orthogroups_numbers_match_yes_ch)

head(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_UPPER_LIPS)

Extract all V.tsujii significantly upregulated bioluminescent upper lip genes from orthogroups shared across both upper lips

#now extract all transcripts 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids <- as.character(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_UPPER_LIPS$Vargula_tsujii_cdhit_95.fasta.transdecoder)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist  <- unlist(strsplit(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids,","))

#remove p* 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist_removep <- vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist %>% str_replace("(.p1)", "") %>% 
str_replace("(.p2)", "")

#remove extra space in front of transcript ids

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist_removep_trimws <- trimws(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist_removep)

vtsujii_bio_upper_lip_orthogroups_transcript_ids <- vtsujii_bio_upper_lip %>% filter (transcript_id %in% vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_BIO_UPPER_LIPS_transcript_ids_unlist_removep_trimws)

head(vtsujii_bio_upper_lip_orthogroups_transcript_ids)

nrow(vtsujii_bio_upper_lip_orthogroups_transcript_ids)

#write.csv(vtsujii_bio_upper_lip_orthogroups_transcript_ids, file = "vtsujii_bio_upper_lip_orthogroups_transcript_ids.csv")

shared_bio_upper_lip_transcript_ids <- vtsujii_bio_upper_lip_orthogroups_transcript_ids$transcript_id

shared_bio_upper_lip_transcript_ids

Extract all Skogsbergia sp. significantly upregulated bioluminescent upper lip genes from orthogroups shared across both upper lips

#now extract all transcripts 

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids <- as.character(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_UPPER_LIPS$Skogsbergia_sp)

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist  <- unlist(strsplit(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids,","))

#remove p* 
vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist_removep <- vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist %>% str_replace("(.p1)", "") %>% 
str_replace("(.p2)", "")

#remove white spaces 

vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist_removep_trimws <- trimws(vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist_removep)

skogs_upper_lip_orthogroups_transcript_ids <- unique_genes_upper_lip_info_annot %>% filter (transcript_id %in% vargulatsujii_v_skogsbergia_SHARED_ORTHOGROUPS_skogs_UPPER_LIP_transcript_ids_unlist_removep_trimws)

head(skogs_upper_lip_orthogroups_transcript_ids)

#write.csv(skogs_upper_lip_orthogroups_transcript_ids, file = "skogs_upper_lip_orthogroups_transcript_ids.csv")

nrow(skogs_upper_lip_orthogroups_transcript_ids)

shared_skogs_transcript_ids <- skogs_upper_lip_orthogroups_transcript_ids$transcript_id

shared_skogs_transcript_ids

DGE - GO enrichment analyses for upper lip

Use topGO to identify enriched biological processes in the upper lip

#import the trinotate go sheet from Trinotate output
geneID2GO <- readMappings(file ="go_annotations_cdhit90_longestisoform.txt")

#save the transcript ids of all the annotated genes under geneNames object 
geneNames<- as.character(Trinotate_lym_subset_skogs$transcript_id)

#significantly upregulated genes (i.e. expressed uniquely) in the upper lip 
head(unique_genes_upper_lip_info)

#save the transcript 
myInterestingGenes= as.character(unique_genes_upper_lip_info$transcript_id)

#subset the genesNames by the transcript IDs in my red module 
geneList <- factor(as.integer(geneNames %in% myInterestingGenes))
names(geneList) <- geneNames
head(geneList)

#run the topGO function for BP 
GOdata <- new("topGOdata", ontology = "BP", allGenes = geneList,
                    annot = annFUN.gene2GO, gene2GO = geneID2GO)

Building most specific GOs .....

	( 15239 GO terms found. )


Build GO DAG topology ..........

	( 15990 GO terms and 37503 relations. )


Annotating nodes ...............

	( 25887 genes annotated to the GO terms. )

results_go <- runTest(GOdata, algorithm="weight01", statistic="Fisher")

			 -- Weight01 Algorithm -- 

		 the algorithm is scoring 2274 nontrivial nodes
		 parameters: 
			 test statistic: fisher


	 Level 19:	1 nodes to be scored	(0 eliminated genes)


	 Level 18:	1 nodes to be scored	(0 eliminated genes)


	 Level 17:	1 nodes to be scored	(2 eliminated genes)


	 Level 16:	3 nodes to be scored	(13 eliminated genes)


	 Level 15:	12 nodes to be scored	(25 eliminated genes)


	 Level 14:	22 nodes to be scored	(133 eliminated genes)


	 Level 13:	41 nodes to be scored	(497 eliminated genes)


	 Level 12:	75 nodes to be scored	(1685 eliminated genes)


	 Level 11:	119 nodes to be scored	(4443 eliminated genes)


	 Level 10:	178 nodes to be scored	(7832 eliminated genes)


	 Level 9:	249 nodes to be scored	(10815 eliminated genes)


	 Level 8:	290 nodes to be scored	(13231 eliminated genes)


	 Level 7:	358 nodes to be scored	(15895 eliminated genes)


	 Level 6:	362 nodes to be scored	(20011 eliminated genes)


	 Level 5:	292 nodes to be scored	(22509 eliminated genes)


	 Level 4:	166 nodes to be scored	(24221 eliminated genes)


	 Level 3:	84 nodes to be scored	(25132 eliminated genes)


	 Level 2:	19 nodes to be scored	(25518 eliminated genes)


	 Level 1:	1 nodes to be scored	(25827 eliminated genes)

#retrieve the GO enrichment 
goEnrichment   <- GenTable(GOdata, Fisher = results_go, orderBy = "Fisher", topNodes = 10000, numChar=1000)

goEnrichment$Fisher <- as.numeric(goEnrichment$Fisher)
goEnrichment <- goEnrichment[goEnrichment$Fisher < 0.05,] 
goEnrichment <- goEnrichment[goEnrichment$Significant > 1,] 
goEnrichment <- goEnrichment[,c("GO.ID","Term", "Annotated", "Significant", "Expected", "Fisher")]
goEnrichment

#write.table(goEnrichment, "df_TopGO_Skogsbergia_sp_DE_unique_Upper_Lip_BP.tsv",sep = "\t", quote=FALSE)

myterms =goEnrichment$GO.ID 
mygenes = genesInTerm(GOdata, myterms)

#extract the transcript ids for each GO term
var=c()
for (i in 1:length(myterms))
{
   myterm <- myterms[i]
   mygenesforterm <- mygenes[myterm][[1]]
   myfactor <- mygenesforterm %in% myInterestingGenes
   mygenesforterm2 <- mygenesforterm[myfactor == TRUE]
   mygenesforterm2 <- paste(mygenesforterm2, collapse=',')
   var[i]=paste(myterm,"genes:",mygenesforterm2)
}

# GO enrichment Upper Lip - BP 

ntop = 50
ggdata <- goEnrichment[1:ntop,]
ggdata$Term <- factor(ggdata$Term, levels = rev(ggdata$Term)) 
plot_GO_UL_BP <- ggplot(ggdata,
  aes(x = Term, y = -log10(Fisher), size = Significant, fill = -log10(Fisher))) +

  expand_limits(y = 1) +
  geom_point(shape = 21) +
  scale_size(range = c(2,7)) +
  scale_fill_continuous(low = 'royalblue', high = 'red4') +

  labs(
    title = 'GO Analysis - Biological Process')+
   theme_bw(base_size = 24) +
labs(size= "Number of Genes")+
  theme(
    legend.position = 'right',
    legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.subtitle = element_text(angle = 0, size = 10, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 12, face = 'bold', vjust = 1),

   axis.text.x = element_blank(),
    axis.text.y = element_text(angle = 0, size = 13, face = 'bold', vjust = 0.5),
    axis.title.x = element_blank(),
    axis.title.y = element_text(size = 8, face = 'bold'),
    axis.line = element_line(colour = 'black'),

    legend.key = element_blank(),
    legend.text = element_text(size = 14, face = "bold"), 
    title = element_text(size = 14, face = "bold")) +


  coord_flip()

#dev.off()

plot_GO_UL_BP + labs(x = NULL)

#library (repr)
options(repr.plot.width=12, repr.plot.height=8, repr.plot.res = 500)

Use topGO to identify enriched molecular functions in the upper lip

#run the topGO function 
GOdata_MF <- new("topGOdata", ontology = "MF", allGenes = geneList,
                    annot = annFUN.gene2GO, gene2GO = geneID2GO)

Building most specific GOs .....

	( 4594 GO terms found. )


Build GO DAG topology ..........

	( 4632 GO terms and 6032 relations. )


Annotating nodes ...............

	( 25806 genes annotated to the GO terms. )

results_go_MF <- runTest(GOdata_MF, algorithm="weight01", statistic="Fisher")

			 -- Weight01 Algorithm -- 

		 the algorithm is scoring 397 nontrivial nodes
		 parameters: 
			 test statistic: fisher


	 Level 12:	3 nodes to be scored	(0 eliminated genes)


	 Level 11:	4 nodes to be scored	(0 eliminated genes)


	 Level 10:	5 nodes to be scored	(45 eliminated genes)


	 Level 9:	15 nodes to be scored	(260 eliminated genes)


	 Level 8:	23 nodes to be scored	(2465 eliminated genes)


	 Level 7:	57 nodes to be scored	(6712 eliminated genes)


	 Level 6:	71 nodes to be scored	(7530 eliminated genes)


	 Level 5:	88 nodes to be scored	(10807 eliminated genes)


	 Level 4:	81 nodes to be scored	(14917 eliminated genes)


	 Level 3:	39 nodes to be scored	(21292 eliminated genes)


	 Level 2:	10 nodes to be scored	(23253 eliminated genes)


	 Level 1:	1 nodes to be scored	(25443 eliminated genes)

#retrieve the GO enrichment 
goEnrichment_MF   <- GenTable(GOdata_MF, Fisher = results_go_MF, orderBy = "Fisher", topNodes = 100, numChar=1000)

#lets graph the GO enrichment (I adapted this code from online)
goEnrichment_MF$Fisher <- as.numeric(goEnrichment_MF$Fisher)
goEnrichment_MF <- goEnrichment_MF[goEnrichment_MF$Fisher < 0.05,] 
goEnrichment_MF <- goEnrichment_MF[goEnrichment_MF$Significant > 1,] 
goEnrichment_MF <- goEnrichment_MF[,c("GO.ID","Term", "Annotated", "Significant", "Expected", "Fisher")]
goEnrichment_MF

#write.table(goEnrichment_MF, "df_TopGO_Skogsbergia_sp_DE_unique_Upper_Lip_MF.tsv",sep = "\t", quote=FALSE)

# GO enrichment Upper Lip - MF 

ntop = 22
ggdata <- goEnrichment_MF[1:ntop,]
ggdata$Term <- factor(ggdata$Term, levels = rev(ggdata$Term)) 
plot_GO_UL_MF <- ggplot(ggdata,
  aes(x = Term, y = -log10(Fisher), size = Significant, fill = -log10(Fisher))) +

  expand_limits(y = 1) +
  geom_point(shape = 21) +
  scale_size(range = c(2,7)) +
  scale_fill_continuous(low = 'royalblue', high = 'red4') +

  labs(
    title = 'GO Analysis - Molecular Function')+
   theme_bw(base_size = 24) +
labs(size= "Number of Genes")+
  theme(
    legend.position = 'right',
    legend.background = element_rect(),
    plot.title = element_text(angle = 0, size = 16, face = 'bold', vjust = 1),
    plot.subtitle = element_text(angle = 0, size = 10, face = 'bold', vjust = 1),
    plot.caption = element_text(angle = 0, size = 12, face = 'bold', vjust = 1),

   axis.text.x = element_blank(),
    axis.text.y = element_text(angle = 0, size = 13, face = 'bold', vjust = 0.5),
    axis.title.x = element_blank(),
    axis.title.y = element_text(size = 8, face = 'bold'),
    axis.line = element_line(colour = 'black'),

    legend.key = element_blank(),
    legend.text = element_text(size = 14, face = "bold"), 
    title = element_text(size = 14, face = "bold")) +


  coord_flip()

#dev.off()

plot_GO_UL_MF +labs(x=NULL)

#library (repr)
options(repr.plot.width=8, repr.plot.height=5)

WGCNA

To determine if the BCN shares similarities and is conserved in the co-expression networks of the non-bioluminescent relative, we checked whether genes in the BCN that are orthologous to genes in the Skogsbergia sp. transcriptome are conserved in their interactions in co-expression networks of Skogsbergia sp.. Co-expression networks for Skogsbergia sp. were generated with WGCNA using 15 total samples from three tissues (upper lip, gut, and compound eye), each with 5 biological replicates. WGCNA (Weighted Gene Co-expression Network Analysis) identifies clusters (modules) of highly correlated genes by constructing a network based on pairwise correlations between gene expression profiles (Langfelder and Horvath, 2008). These modules often correspond to specific biological processes or pathways, indicating that the genes within a module may be part of the same regulatory process. By analyzing the connectivity of genes within each module, WGCNA also helps identify key drivers or hub genes, providing insights into gene regulation and the biological processes they govern. The following scripts are from the WGCNA package (Langfelder and Horvath, 2008).

Run WGCNA

#grab the count matrix from the DEseq2 object 
vsd_matrix <- assay(vsd_prefiltered_wgcna)
## many functions expect the matrix to be transposed
datExpr <- t(vsd_matrix) 
## check rows/cols
nrow(datExpr)
ncol(datExpr)

head(datExpr)

head(vsd_matrix)

#run this to check if there are gene outliers
gsg=goodSamplesGenes(datExpr, verbose = 3)
gsg$allOK

 Flagging genes and samples with too many missing values...
  ..step 1

# Choose a set of soft-thresholding powers
powers = c(c(1:10), seq(from = 12, to=20, by=2))
# Call the network topology analysis function
sft = pickSoftThreshold(datExpr, powerVector = powers, verbose = 5)

pickSoftThreshold: will use block size 1726.
 pickSoftThreshold: calculating connectivity for given powers...
   ..working on genes 1 through 1726 of 25909
   ..working on genes 1727 through 3452 of 25909
   ..working on genes 3453 through 5178 of 25909
   ..working on genes 5179 through 6904 of 25909
   ..working on genes 6905 through 8630 of 25909
   ..working on genes 8631 through 10356 of 25909
   ..working on genes 10357 through 12082 of 25909
   ..working on genes 12083 through 13808 of 25909
   ..working on genes 13809 through 15534 of 25909
   ..working on genes 15535 through 17260 of 25909
   ..working on genes 17261 through 18986 of 25909
   ..working on genes 18987 through 20712 of 25909
   ..working on genes 20713 through 22438 of 25909
   ..working on genes 22439 through 24164 of 25909
   ..working on genes 24165 through 25890 of 25909
   ..working on genes 25891 through 25909 of 25909
   Power SFT.R.sq  slope truncated.R.sq mean.k. median.k. max.k.
1      1   0.3770  4.520          0.949  7330.0   7100.00  10900
2      2   0.0518  0.660          0.834  3050.0   2800.00   6120
3      3   0.0748 -0.511          0.758  1530.0   1310.00   3940
4      4   0.5370 -1.230          0.857   858.0    690.00   2790
5      5   0.8210 -1.610          0.945   523.0    391.00   2100
6      6   0.9170 -1.750          0.974   339.0    236.00   1640
7      7   0.9540 -1.810          0.983   230.0    149.00   1330
8      8   0.9740 -1.810          0.989   162.0     98.20   1110
9      9   0.9800 -1.810          0.989   118.0     66.60    950
10    10   0.9870 -1.800          0.991    88.7     46.60    827
11    12   0.9940 -1.740          0.994    53.3     24.40    652
12    14   0.9980 -1.690          0.997    34.4     13.70    534
13    16   0.9970 -1.620          0.997    23.6      8.16    450
14    18   0.9950 -1.560          0.996    16.9      5.09    388
15    20   0.9920 -1.510          0.995    12.6      3.31    340

# Plot the results
cex1 = 0.9;
# Scale-free topology fit index as a function of the soft-thresholding power
plot(sft$fitIndices[,1], -sign(sft$fitIndices[,3])*sft$fitIndices[,2],
     xlab="Soft Threshold (power)",ylab="Scale Free Topology Model Fit,signed R^2",type="n",
     main = paste("Scale independence"));
text(sft$fitIndices[,1], -sign(sft$fitIndices[,3])*sft$fitIndices[,2],
     labels=powers,cex=cex1,col="red");
# this line corresponds to using an R^2 cut-off of h
abline(h=0.90,col="red")
# Mean connectivity as a function of the soft-thresholding power
plot(sft$fitIndices[,1], sft$fitIndices[,5],
     xlab="Soft Threshold (power)",ylab="Mean Connectivity", type="n",
     main = paste("Mean connectivity"))
text(sft$fitIndices[,1], sft$fitIndices[,5], labels=powers, cex=cex1,col="red")

# Co-expression similarity and adjacency using assigned softpower
softPower=7
adjacency = adjacency(datExpr, power = softPower)

# Topological Overlap Matrix (TOM)
# Turn adjacency into topological overlap, i.e. translate the adjacency into 
# topological overlap matrix and calculate the corresponding dissimilarity:
TOM = TOMsimilarity(adjacency, TOMType = "signed", verbose = 5);
dissTOM = 1-TOM;

..connectivity..
..matrix multiplication (system BLAS)..
..normalization..
..done.

# Call the hierarchical clustering function
geneTree = hclust(as.dist(dissTOM), method = "average");

minModuleSize = 50
# Module identification using dynamic tree cut:
dynamicMods = cutreeDynamic(dendro = geneTree, distM = dissTOM,
                deepSplit = 2, pamRespectsDendro = FALSE,
                minClusterSize = minModuleSize);

 ..cutHeight not given, setting it to 0.993  ===>  99% of the (truncated) height range in dendro.
 ..done.

table(dynamicMods)
dynamicColors = labels2colors(dynamicMods)

dynamicMods
   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
4054  676  661  425  407  377  372  365  360  348  346  314  275  264  256  254 
  17   18   19   20   21   22   23   24   25   26   27   28   29   30   31   32 
 239  239  232  231  230  225  224  222  221  220  214  214  211  209  205  201 
  33   34   35   36   37   38   39   40   41   42   43   44   45   46   47   48 
 199  197  195  195  192  186  183  183  182  181  171  165  164  164  164  163 
  49   50   51   52   53   54   55   56   57   58   59   60   61   62   63   64 
 160  159  158  157  154  151  150  150  149  146  144  144  144  143  142  142 
  65   66   67   68   69   70   71   72   73   74   75   76   77   78   79   80 
 141  140  139  138  138  138  136  136  135  134  133  131  130  129  129  128 
  81   82   83   84   85   86   87   88   89   90   91   92   93   94   95   96 
 127  127  127  127  127  125  124  124  123  122  122  121  121  120  120  119 
  97   98   99  100  101  102  103  104  105  106  107  108  109  110  111  112 
 119  116  116  115  112  112  111  109  109  108  106  105  104  104  103  103 
 113  114  115  116  117  118  119  120  121  122  123  124  125  126  127  128 
 102  101  101   99   99   97   96   95   94   86   84   84   84   82   81   73

table(dynamicColors)

dynamicColors
  antiquewhite1   antiquewhite2   antiquewhite4         bisque4           black 
             96             122             144             164             372 
           blue           blue2           blue4      blueviolet           brown 
            676             131             109             109             661 
         brown2          brown4      chocolate4           coral          coral1 
            133             164              97             123             144 
         coral2          coral3          coral4            cyan       darkgreen 
            143             122              95             264             225 
       darkgrey     darkmagenta  darkolivegreen darkolivegreen2 darkolivegreen4 
            222             197             199             111             134 
     darkorange     darkorange2         darkred   darkseagreen2   darkseagreen3 
            220             164             230              99             124 
  darkseagreen4   darkslateblue   darkturquoise      darkviolet        deeppink 
            144             163             224             130             108 
     firebrick3      firebrick4     floralwhite           green          green4 
            112             135             165             407              99 
    greenyellow          grey60        honeydew       honeydew1      indianred3 
            346             239             124             146             112 
     indianred4           ivory  lavenderblush1  lavenderblush2  lavenderblush3 
            136             171             101             125             149 
     lightblue4      lightcoral       lightcyan      lightcyan1      lightgreen 
            115             136             254             181             239 
     lightpink2      lightpink3      lightpink4   lightskyblue4  lightslateblue 
            101             127             150              73             116 
 lightsteelblue lightsteelblue1     lightyellow         magenta        magenta3 
            138             182             232             360             102 
       magenta4          maroon    mediumorchid    mediumpurple   mediumpurple1 
            127             150             142              81             116 
  mediumpurple2   mediumpurple3   mediumpurple4    midnightblue       mistyrose 
            138             183             121             256              94 
    navajowhite    navajowhite1    navajowhite2          orange       orangered 
            103             127             151             221              82 
     orangered1      orangered3      orangered4   paleturquoise  palevioletred1 
            119             138             183             205             103 
 palevioletred2  palevioletred3            pink           pink3           pink4 
            127             154             365              84             119 
           plum           plum1           plum2           plum3           plum4 
            139             186             160             129             106 
         purple             red       royalblue     saddlebrown          salmon 
            348             377             231             211             275 
        salmon1         salmon2         salmon4         sienna2         sienna3 
            104             127             157              84             195 
        sienna4         skyblue        skyblue1        skyblue2        skyblue3 
            120             214             140             142             192 
       skyblue4       slateblue       steelblue             tan            tan4 
            121              86             209             314             104 
        thistle        thistle1        thistle2        thistle3        thistle4 
            128             158             159             129             105 
      turquoise          violet           white          yellow         yellow2 
           4054             201             214             425              84 
        yellow3         yellow4     yellowgreen 
            120             141             195

# Plot the dendrogram and colors underneath
#sizeGrWindow(8,6)
plotDendroAndColors(geneTree, dynamicColors, "Dynamic Tree Cut",
                    dendroLabels = FALSE, hang = 0.03,
                    addGuide = TRUE, guideHang = 0.05,
                    main = "Gene dendrogram and module colors")

# Calculate eigengenes
MEList = moduleEigengenes(datExpr, colors = dynamicColors)
MEs = MEList$eigengenes
# Calculate dissimilarity of module eigengenes
MEDiss = 1-cor(MEs);
# Cluster module eigengenes
METree = hclust(as.dist(MEDiss), method = "average");
# Plot the result
#sizeGrWindow(7, 6)
plot(METree, main = "Clustering of module eigengenes",
     xlab = "", sub = "")
MEDissThres = 0.30
# Plot the cut line into the dendrogram
abline(h=MEDissThres, col = "red")

# Call an automatic merging function
merge = mergeCloseModules(datExpr, dynamicColors, cutHeight = MEDissThres, verbose = 3)
# The merged module colors
mergedColors = merge$colors;
# Eigengenes of the new merged modules:
mergedMEs = merge$newMEs;

 mergeCloseModules: Merging modules whose distance is less than 0.3
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 128 module eigengenes in given set.
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 72 module eigengenes in given set.
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 55 module eigengenes in given set.
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 50 module eigengenes in given set.
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 49 module eigengenes in given set.
   Calculating new MEs...
   multiSetMEs: Calculating module MEs.
     Working on set 1 ...
     moduleEigengenes: Calculating 49 module eigengenes in given set.

plotDendroAndColors(geneTree, cbind(dynamicColors, mergedColors),
                    c("Dynamic Tree Cut", "Merged dynamic"),
                    dendroLabels = FALSE, hang = 0.03,
                    addGuide = TRUE, guideHang = 0.05)

table(mergedColors)

mergedColors
 antiquewhite2  antiquewhite4        bisque4          black           blue 
           489            594            164            619            676 
         blue2          blue4          brown         brown2         brown4 
          1953            109            800            239            848 
    chocolate4         coral1         coral4           cyan       darkgrey 
           220            699           2352           1183           1265 
   darkmagenta        darkred  darkseagreen2  darkseagreen3  darkturquoise 
           798            230             99            236            548 
    darkviolet       deeppink          green         green4       honeydew 
           559            108            407             99            225 
lavenderblush3     lightgreen     lightpink2     lightpink3  lightskyblue4 
           697            911            101            127             73 
 mediumpurple2  mediumpurple3  mediumpurple4   midnightblue      mistyrose 
           224            183            121            256            251 
   navajowhite   navajowhite2         orange      orangered palevioletred1 
           103            151            221            966            103 
          pink          plum1        salmon1        skyblue       skyblue1 
           365            328            104            214            140 
           tan           tan4      turquoise        yellow2 
           509            104           4054             84

Module to trait heatmap

Identify modules (network) that are significantly associated with samples. The module eigengene provides a representative measure of the gene expression patterns within a module, allowing correlation with these traits to determine the most significant associations (Langfelder and Horvath, 2008). This correlation can then be visualized in a module-to-trait heatmap to determine the most significant associations.The following scripts are from the WGCNA package (Langfelder and Horvath, 2008).

skogs_traits <- read_excel("skogs_trait.xlsx")

skogs_traits

sample_names_numeric <- c("1", "2", "3", "1", "2" ,"3", "1", "2", "3", "1", "2", "3", "1", "2", "3")

skogs_traits$sample_names_numeric <- sample_names_numeric

skogs_traits

sample_name

skogsSamples =as.character(sample_name)
traitRows =match(skogsSamples,skogs_traits$Tissue_Type)

traitRows

skogsTraits =skogs_traits[traitRows, -1]

skogsTraits

rownames(skogsTraits)=skogs_traits$Sample_Name

Warning message:
“Setting row names on a tibble is deprecated.”

skogsTraits$Tissue_Type <- NULL

skogsTraits$sample_names_numeric <- NULL

rownames(skogsTraits)=skogs_traits$Sample_Name

Warning message:
“Setting row names on a tibble is deprecated.”

skogsTraits

# Re-cluster samples
sampleTree2 = hclust(dist(datExpr), method = "average")
# Convert traits to a color representation: white means low, red means high, grey means missing entry
traitColors = numbers2colors(skogsTraits, signed = FALSE);
# Plot the sample dendrogram and the colors underneath.
plotDendroAndColors(sampleTree2, traitColors,
                    groupLabels = names(skogsTraits),
                    main = "Sample dendrogram and trait heatmap")

#Define numbers of genes and samples
nGenes = ncol(datExpr);
nSamples = nrow(datExpr);

mergedMEs

names(mergedMEs)
moduleTraitCor = cor(mergedMEs, skogsTraits, use = "p");
moduleTraitPvalue = corPvalueStudent(moduleTraitCor, nSamples);

#view the graph
# Will display correlations and their p-values
textMatrix = paste(signif(moduleTraitCor, 2), "\n(",
                   signif(moduleTraitPvalue, 1), ")", sep = "");
dim(textMatrix) = dim(moduleTraitCor)

par(mar = c(6, 10, 6, 1) )
# Display the correlation values within a heatmap plot
labeledHeatmap(moduleTraitCor,
               xLabels = names(skogsTraits),
               yLabels = names(mergedMEs),
               ySymbols = names(mergedMEs),
               colorLabels = FALSE,
               colors = blueWhiteRed(50),
              textMatrix = textMatrix,
               setStdMargins = FALSE,
               cex.text = 0.5,
               textAdj = c(0.5, 0.5),
               zlim = c(-1,1),
               main = paste("Module-trait relationships"))

#library (repr)
options(repr.plot.width=10, repr.plot.height=10)

WGCNA Function

wgcna_adjacency <- function(datExpr, minModuleSize=50, MEDissThres = .30, deepSplit = 2) {
 
  #compute adjacency
  adjacency <- adjacency(datExpr, power = 7)
  TOM <- TOMsimilarity(adjacency,TOMType="signed")
  geneTree <- hclust(as.dist(1-TOM), method = "average")
    


  # Module identification using dynamic tree cut:
  dynamicMods <- cutreeDynamic(dendro = geneTree, distM = 1-TOM, deepSplit = 2, pamRespectsDendro = FALSE, minClusterSize = minModuleSize);
  table(dynamicMods)
  dynamicColors = labels2colors(dynamicMods)

  # Calculate eigengenes
  MEList = moduleEigengenes(datExpr, colors = dynamicColors)
  MEs = MEList$eigengenes
  # Calculate dissimilarity of module eigengenes
  METree = hclust(as.dist(1-cor(MEs)), method = "average");
  plot(METree, main = "Clustering of module eigengenes",xlab = "", sub = "")
  # Plot the cut line into the dendrogram
  abline(h=MEDissThres, col = "red")

  merge <- mergeCloseModules(datExpr, dynamicColors, cutHeight = MEDissThres, verbose = 0)

  # The merged module colors
  mergedColors = merge$colors
  # Eigengenes of the new merged modules:
  mergedMEs = merge$newMEs
  
  # Rename to moduleColors
  moduleColors = mergedColors
  # Construct numerical labels corresponding to the colors
  colorOrder = c("grey", standardColors(50));
  moduleLabels = match(moduleColors, colorOrder)-1;
  MEs = mergedMEs;

  # Recalculate MEs with color labels
  invisible(MEs0 <- moduleEigengenes(datExpr, moduleColors)$eigengenes)
  MEs = orderMEs(MEs0)

  print(table(moduleColors))
  moduleColors <- as.data.frame(moduleColors)
  rownames(moduleColors) <- colnames(datExpr)

  return(list(adjacency=adjacency,MEs=MEs,moduleColors=moduleColors, dynamicMods=dynamicMods, geneTree=geneTree))
}

wgcna.results <- wgcna_adjacency(datExpr, MEDissThres = 0.30)

..connectivity..
..matrix multiplication (system BLAS)..
..normalization..
..done.
 ..cutHeight not given, setting it to 0.993  ===>  99% of the (truncated) height range in dendro.
 ..done.
moduleColors
 antiquewhite2  antiquewhite4        bisque4          black           blue 
           489            594            164            619            676 
         blue2          blue4          brown         brown2         brown4 
          1953            109            800            239            848 
    chocolate4         coral1         coral4           cyan       darkgrey 
           220            699           2352           1183           1265 
   darkmagenta        darkred  darkseagreen2  darkseagreen3  darkturquoise 
           798            230             99            236            548 
    darkviolet       deeppink          green         green4       honeydew 
           559            108            407             99            225 
lavenderblush3     lightgreen     lightpink2     lightpink3  lightskyblue4 
           697            911            101            127             73 
 mediumpurple2  mediumpurple3  mediumpurple4   midnightblue      mistyrose 
           224            183            121            256            251 
   navajowhite   navajowhite2         orange      orangered palevioletred1 
           103            151            221            966            103 
          pink          plum1        salmon1        skyblue       skyblue1 
           365            328            104            214            140 
           tan           tan4      turquoise        yellow2 
           509            104           4054             84

#wgcna.results 
dynamicColors<- labels2colors(wgcna.results$dynamicMods)
merge <- mergeCloseModules(datExpr, dynamicColors, cutHeight = 0.30, verbose = 0) 
mergedColors<-merge$colors
mergedMEs<-merge$newMEs

Determine the number of Skogsbergia sp. networks that contain BCN one-to-one orthologs

vsd_matrix_df <- as.data.frame(vsd_matrix)

vsd_matrix_df$colors <- wgcna.results[["moduleColors"]]$moduleColors

head(vsd_matrix_df)

#how to make rownames the first column 
vsd_matrix_df$transcript_id <-rownames(vsd_matrix_df)

transcripts_to_module <- na.omit(vsd_matrix_df) %>% dplyr::select(transcript_id, colors)

head(transcripts_to_module)

BCN_on_to_one_orthologs_skogs_networks <- transcripts_to_module %>% filter(transcript_id %in% BCN_one_to_one_orthologs_skogs$transcript_id)

BCN_on_to_one_orthologs_skogs_networks_ordered_color <- BCN_on_to_one_orthologs_skogs_networks %>% arrange(colors)

BCN_on_to_one_orthologs_skogs_networks_ordered_color

# the BCN one to one orthologs are found across 24 modules 
length(unique(BCN_on_to_one_orthologs_skogs_networks_ordered_color$colors))

as.data.frame(table(BCN_on_to_one_orthologs_skogs_networks_ordered_color$colors))

Module info

To test the hypothesis of biological significance for co-expression modules, it was checked whether modules correlated with eye tissue contain genes related to eye function and development.

SubGeneNames = colnames(datExpr)

green_eye_module=as.data.frame(SubGeneNames[which(mergedColors=="green")])
#match the nodes 
names(green_eye_module)[1] <- "transcript_id"
green_eye_module_trinotate <- setDT(Trinotate_lym_subset_skogs, key = 'transcript_id')[J(green_eye_module)]
#write.csv( green_eye_module, file = "green_eye_module_Skogs.csv")

head(green_eye_module_trinotate)

Determine if BCN one-to-one orthologs are conserved in Skogsbergia sp. networks

To determine whether the BCN is conserved, a randomization test was performed to assess if 51 BCN orthologs, selected at random from all possible one-to-one expressed orthologs, are found in fewer modules than a random set of genes

#import the BCN one-to-one ortholog sheet 

BCN_one_to_one_orthologs_skogs <- read.csv("BCN_one_to_one_orthologs_skogs_ids_unlist_removep_unique.csv" ,header = TRUE, row.names=1, stringsAsFactors = FALSE)

head(BCN_one_to_one_orthologs_skogs)

colnames(BCN_one_to_one_orthologs_skogs)[1] <- "transcript_id"

#total of 79 one to one orthologs across V.tsujii and Skogsbergia sp. transcriptomes but only 51 transcripts are expressed in the networks of Skogsbergia sp. 
nrow(BCN_one_to_one_orthologs_skogs)

#import ALL the one-to-one orthologs  V.tsujii and Skogsbergia sp. transcriptomes.

ALL_one_to_one_orthologs_vtsujii_skogs <- read.csv("ALL_one_to_one_orthologs_vtsujii_skogs.csv" ,header = TRUE, row.names=1, stringsAsFactors = FALSE)

head(ALL_one_to_one_orthologs_vtsujii_skogs)

#now lets just subset the Skogsbergia column for the randomization test 
ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS <-  subset(ALL_one_to_one_orthologs_vtsujii_skogs, select ="skogs")

head(ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS)

#need to remove .p1 

ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep <- ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS %>% separate(skogs, c("transcript_id", "extra"), sep ="\\.p")

ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep$extra <- NULL

ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep_rmdup <- ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep %>% distinct()

nrow(ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep_rmdup)

# now subset this to include all transripts expressed in Skogsbergia sp. networks

dds_merged_table_prefiltered_wgcna_transcript_ids <- as.data.frame(rownames(dds_merged_table_prefiltered_wgcna))

colnames(dds_merged_table_prefiltered_wgcna_transcript_ids)[1] <- "transcript_id"

#now subset

ALL_one_to_one_orthologs_skogs_SUBSET_to_wgcna_expression_input  <- subset(ALL_one_to_one_orthologs_vtsujii_skogs_SUBSET_SKOGS_removep_rmdup, transcript_id %in% dds_merged_table_prefiltered_wgcna_transcript_ids$transcript_id)

head(ALL_one_to_one_orthologs_skogs_SUBSET_to_wgcna_expression_input)

nrow(ALL_one_to_one_orthologs_skogs_SUBSET_to_wgcna_expression_input)

#perform the randomization test
#total of 79 one to one orthologs across V.tsujii and Skogsbergia sp. transcriptomes but only 51 transcripts are expressed in the networks of Skogsbergia sp. 
ALL_one_to_one_orthologs_skogs_df_repeat10000 <- replicate(10000, sample(ALL_one_to_one_orthologs_skogs_SUBSET_to_wgcna_expression_input$transcript_id, size = 51, replace = FALSE))

head(ALL_one_to_one_orthologs_skogs_df_repeat10000)

#function to extract the number of Skogsbergia sp. modules in which one-to-one BCN orthologs are found for the randomization test

matrix_1 <- c()
matrix_2 <- c()
matrix_3 <-c()


for(i in 1:ncol(ALL_one_to_one_orthologs_skogs_df_repeat10000 )){
matrix_1[[i]] <- ALL_one_to_one_orthologs_skogs_df_repeat10000 [ ,i]
matrix_2[[i]] <- transcripts_to_module %>% filter(transcript_id %in% matrix_1[[i]])
matrix_3[[i]]<- length(unique(matrix_2[[i]]$colors))

}


print(matrix_3)

    [1] 19 23 23 21 19 23 21 18 23 25 19 29 21 23 23 17 21 25 21 20 18 18 26 16
   [25] 27 26 22 23 21 26 22 23 23 21 21 22 22 23 22 24 21 23 19 24 25 23 18 24
   [49] 20 20 24 22 21 25 24 20 22 22 24 22 18 22 19 24 24 20 27 22 25 26 22 17
   [73] 21 21 20 19 24 26 27 22 25 17 25 23 20 23 21 23 22 25 24 23 23 20 19 22
   [97] 20 26 22 27 20 20 24 24 24 21 24 24 21 25 17 26 21 24 22 26 22 20 24 25
  [121] 20 24 25 21 23 27 22 23 20 24 24 21 22 21 19 23 23 24 25 22 24 19 20 20
  [145] 17 20 17 17 21 26 25 24 25 22 20 20 24 19 25 23 19 21 23 20 23 21 19 25
  [169] 21 20 21 20 22 21 24 21 21 23 20 22 22 24 20 25 16 29 23 24 18 18 25 21
  [193] 26 21 20 20 23 22 23 22 22 25 21 20 24 21 20 21 29 19 22 22 22 21 22 20
  [217] 25 20 20 21 28 19 26 23 24 21 25 22 26 26 22 22 20 22 20 21 26 22 26 21
  [241] 25 24 23 20 24 24 22 22 18 23 23 25 24 20 20 24 25 25 24 21 22 21 25 23
  [265] 23 20 23 24 22 21 20 23 19 24 25 24 25 21 20 26 20 21 20 20 20 23 20 23
  [289] 24 23 20 24 20 21 24 24 20 21 21 23 19 21 21 23 21 23 21 26 25 20 23 23
  [313] 19 24 25 25 24 20 25 21 24 18 23 22 20 26 19 23 24 24 22 23 20 20 25 29
  [337] 23 21 21 24 21 21 21 23 24 27 23 22 23 19 22 18 23 25 26 23 23 20 25 20
  [361] 24 24 24 23 23 22 22 22 25 20 22 25 19 23 26 24 21 24 21 23 22 24 22 20
  [385] 22 22 22 28 28 17 18 20 24 25 21 23 20 23 22 24 24 22 22 18 22 22 23 14
  [409] 20 20 22 19 22 21 27 24 19 21 23 27 23 21 24 19 21 25 20 25 26 24 22 22
  [433] 21 19 23 24 24 21 23 23 19 17 23 22 21 21 19 23 20 16 23 21 21 16 20 21
  [457] 25 23 26 22 23 21 22 19 18 20 25 19 20 24 24 18 25 20 25 20 20 22 24 25
  [481] 19 23 20 21 27 26 20 24 30 20 23 22 25 19 23 20 21 23 21 22 24 25 18 23
  [505] 23 20 16 21 25 20 24 22 22 20 18 23 23 21 25 25 20 18 19 23 22 21 24 22
  [529] 23 23 24 18 19 23 21 25 26 20 21 21 20 20 27 20 21 26 22 26 22 29 21 26
  [553] 17 24 25 22 22 22 22 20 20 23 24 23 26 18 21 23 24 20 23 20 24 26 21 27
  [577] 20 24 21 21 23 22 26 20 19 21 19 24 26 25 22 20 23 24 15 24 23 20 23 20
  [601] 21 24 18 19 21 23 23 28 23 20 22 23 24 24 20 24 20 20 19 26 21 25 26 20
  [625] 24 24 21 19 27 19 21 20 24 21 20 19 21 24 27 23 25 17 25 23 19 20 23 21
  [649] 27 24 22 25 22 25 25 19 23 26 22 22 23 23 21 22 21 23 19 18 22 24 20 20
  [673] 20 26 25 26 19 22 22 25 20 20 23 25 22 25 25 23 21 19 23 23 22 20 23 22
  [697] 24 22 22 24 23 21 21 23 20 16 24 21 22 24 21 19 26 22 21 20 23 21 17 19
  [721] 25 23 23 23 19 21 25 23 19 23 20 22 25 19 20 20 24 21 19 20 24 21 22 21
  [745] 24 24 21 22 22 20 21 23 23 24 25 17 15 22 24 26 22 20 21 20 21 24 20 22
  [769] 22 22 22 22 23 20 22 22 22 22 26 25 21 26 23 19 19 18 19 22 21 20 22 23
  [793] 22 23 21 20 23 21 22 25 21 26 23 20 24 23 22 24 21 22 22 24 21 26 21 23
  [817] 20 21 20 23 19 22 23 25 23 25 23 21 23 26 25 23 21 22 23 24 23 20 25 23
  [841] 24 18 20 22 21 20 23 20 25 27 24 21 23 21 24 20 19 21 21 22 20 21 24 19
  [865] 19 21 23 22 17 22 21 22 23 21 20 22 24 26 18 23 21 24 23 20 19 23 21 19
  [889] 24 24 20 22 21 23 19 21 23 23 22 23 20 21 23 21 20 20 22 27 18 21 21 22
  [913] 24 19 21 21 23 24 21 22 22 22 21 22 19 20 19 23 19 21 18 22 22 23 21 23
  [937] 25 25 28 23 19 21 18 25 24 22 22 21 21 22 23 24 20 20 21 22 20 18 23 21
  [961] 22 22 25 20 22 21 17 21 22 25 27 19 20 21 18 24 25 19 22 20 20 23 21 25
  [985] 21 22 26 20 20 20 25 20 25 25 25 22 18 24 25 21 20 20 24 22 20 24 20 20
 [1009] 21 21 20 24 23 20 26 25 21 23 20 26 21 24 25 21 21 19 26 24 22 18 25 19
 [1033] 27 19 24 24 22 22 21 24 20 23 22 20 20 23 22 24 27 21 23 18 22 22 21 25
 [1057] 21 22 25 22 25 22 18 20 21 24 24 20 21 21 18 27 23 19 24 23 25 23 22 23
 [1081] 22 21 23 22 23 21 23 23 22 23 27 23 23 21 22 26 19 25 23 21 25 22 25 20
 [1105] 18 19 19 26 19 19 20 21 25 25 21 24 24 19 24 24 23 23 20 22 25 20 23 26
 [1129] 24 21 26 21 20 24 24 21 22 24 26 28 24 20 20 22 21 21 24 25 24 23 19 21
 [1153] 23 21 25 24 21 18 23 24 20 22 22 23 20 23 22 26 24 21 25 21 28 22 24 20
 [1177] 24 21 22 22 20 21 23 22 25 23 24 25 24 21 20 20 21 23 24 24 21 19 23 20
 [1201] 21 25 24 23 22 19 21 23 21 20 20 22 23 21 24 25 21 20 25 20 25 21 20 24
 [1225] 19 21 27 25 26 23 20 24 23 21 22 23 23 19 23 25 23 25 21 23 21 24 21 22
 [1249] 20 23 19 22 20 18 20 24 24 22 24 24 22 22 25 22 23 29 23 22 22 16 26 19
 [1273] 20 23 21 27 22 24 22 21 25 20 26 24 25 18 20 23 18 24 22 22 26 25 21 25
 [1297] 24 23 22 22 22 21 25 23 24 25 22 25 24 19 27 19 20 19 23 21 25 25 20 26
 [1321] 19 24 22 23 24 21 26 22 17 23 24 24 23 22 21 21 20 19 20 24 22 24 23 21
 [1345] 23 22 23 23 24 22 18 20 21 28 25 21 22 21 22 21 27 21 24 25 23 22 22 17
 [1369] 19 19 23 20 24 21 26 23 24 26 20 26 21 21 21 25 21 19 22 26 22 23 16 23
 [1393] 23 22 23 20 25 19 27 23 26 23 22 24 21 21 21 24 22 18 21 25 22 22 25 22
 [1417] 19 26 19 23 23 20 23 22 22 20 25 23 23 21 25 19 24 21 21 24 18 18 24 21
 [1441] 23 21 22 25 20 22 19 18 24 23 23 25 19 21 21 27 22 24 18 20 22 18 22 25
 [1465] 22 19 21 19 22 23 25 27 18 26 25 24 22 20 25 27 22 25 23 23 21 22 21 23
 [1489] 19 22 24 27 25 25 23 24 24 18 25 27 19 20 20 24 19 22 20 18 19 23 20 23
 [1513] 22 23 25 22 22 20 21 19 20 20 20 20 19 25 25 23 24 22 23 20 25 20 17 20
 [1537] 18 22 23 26 17 23 22 23 21 19 20 20 25 23 20 20 20 21 24 25 20 22 19 20
 [1561] 23 23 21 26 23 23 22 21 21 26 21 19 22 19 23 21 22 22 22 25 22 22 21 25
 [1585] 23 22 23 20 23 17 21 22 21 20 24 18 26 23 22 24 24 19 22 22 24 27 20 24
 [1609] 22 24 24 24 19 20 23 14 21 22 26 22 23 27 25 22 22 25 22 22 24 23 24 20
 [1633] 21 19 24 23 23 22 20 20 26 23 23 21 21 23 17 26 26 23 21 20 19 21 21 24
 [1657] 21 24 24 17 22 24 27 21 23 23 18 26 25 19 26 23 20 22 21 24 24 20 26 19
 [1681] 24 22 25 21 23 18 26 20 18 20 20 21 23 22 23 21 19 23 21 17 21 23 19 21
 [1705] 22 23 24 18 24 19 19 21 23 19 20 21 20 24 19 24 20 23 24 22 22 21 23 25
 [1729] 19 25 21 23 24 23 19 22 22 24 23 21 22 24 20 23 23 22 21 21 18 21 21 23
 [1753] 21 22 19 19 23 19 24 26 24 22 21 18 18 22 21 21 23 20 26 22 20 25 19 23
 [1777] 19 22 25 21 23 25 27 22 23 19 21 22 25 20 23 23 22 24 24 24 20 22 24 26
 [1801] 24 21 27 20 24 24 23 18 24 24 23 23 21 24 23 23 24 19 22 22 22 28 22 20
 [1825] 24 22 23 20 25 27 22 26 22 26 23 21 23 20 23 20 20 21 20 22 22 25 22 20
 [1849] 21 19 21 20 26 21 23 20 18 27 24 21 23 23 22 27 22 22 23 25 22 23 21 21
 [1873] 23 25 26 20 22 26 21 25 21 20 23 22 22 24 24 23 22 21 26 24 22 20 21 20
 [1897] 23 20 26 16 23 22 27 21 26 20 25 23 28 23 23 21 18 26 23 24 19 20 22 19
 [1921] 22 22 22 21 18 21 26 20 22 22 23 22 22 18 24 23 17 23 23 17 24 24 25 25
 [1945] 25 20 24 23 18 19 21 24 18 24 24 22 20 21 22 22 21 22 25 24 21 22 21 20
 [1969] 23 25 24 28 20 19 21 21 23 24 26 17 23 23 24 21 21 22 23 23 20 22 25 26
 [1993] 23 19 22 22 20 17 22 21 21 22 23 24 28 23 21 26 19 21 22 20 21 21 21 24
 [2017] 23 25 21 25 19 25 25 22 24 18 26 21 20 21 23 24 20 21 17 22 23 27 23 23
 [2041] 21 21 22 20 21 20 23 19 23 23 18 22 22 26 18 27 19 17 24 20 21 24 21 20
 [2065] 26 18 20 19 20 23 18 20 23 19 23 22 17 22 20 21 25 24 24 22 22 21 22 20
 [2089] 23 24 24 21 20 24 20 24 21 25 25 22 21 18 23 24 18 22 26 22 18 20 23 22
 [2113] 24 25 22 25 23 25 22 24 20 21 20 20 20 23 19 21 20 21 19 25 20 25 23 23
 [2137] 24 24 20 22 25 23 20 18 25 26 18 22 25 21 25 23 24 24 19 21 21 24 24 22
 [2161] 20 21 24 22 24 23 19 22 21 23 24 25 26 21 25 24 21 23 24 20 26 25 22 23
 [2185] 23 25 20 22 22 16 22 24 22 24 22 22 22 21 23 22 22 21 21 22 22 26 28 21
 [2209] 23 23 26 20 25 23 18 20 24 24 17 21 22 18 20 25 19 20 26 26 26 20 20 23
 [2233] 23 22 22 22 19 26 22 21 24 24 20 26 20 26 21 21 22 20 25 22 22 24 22 24
 [2257] 20 25 23 22 24 21 23 23 21 19 23 17 22 24 22 18 20 23 24 23 19 22 20 19
 [2281] 21 21 23 24 23 18 23 27 24 19 20 23 19 23 23 22 19 26 23 22 24 22 26 24
 [2305] 23 23 25 19 24 22 20 18 19 23 22 20 22 24 23 22 19 19 18 20 19 22 22 25
 [2329] 22 22 22 22 20 25 19 22 24 24 18 24 22 22 24 20 24 20 20 23 25 26 24 20
 [2353] 21 25 21 23 19 25 23 25 14 20 22 20 25 19 19 26 19 25 25 18 20 21 21 22
 [2377] 20 18 22 19 21 28 21 23 26 22 25 26 25 23 19 19 26 20 22 22 21 22 22 23
 [2401] 26 20 19 23 25 21 24 19 15 24 20 24 21 20 20 19 23 21 25 24 24 21 19 20
 [2425] 20 24 21 22 24 23 24 15 18 19 21 25 22 25 25 18 25 24 20 23 24 22 20 20
 [2449] 24 18 24 18 22 23 21 23 22 20 23 24 24 24 27 23 24 17 23 20 20 23 20 24
 [2473] 23 20 23 23 17 18 19 25 19 19 22 24 21 21 24 23 23 23 22 23 14 20 27 28
 [2497] 21 25 22 26 24 22 24 22 19 24 21 23 24 22 22 25 22 25 23 23 21 21 22 23
 [2521] 22 20 20 23 20 23 23 23 23 24 25 18 28 25 24 24 21 20 22 24 22 25 21 22
 [2545] 21 21 23 20 23 19 20 24 22 22 25 21 23 26 22 22 18 22 20 26 21 22 23 25
 [2569] 20 21 23 23 24 22 25 22 24 25 20 23 23 23 24 24 20 22 22 24 22 22 22 18
 [2593] 22 22 23 23 21 23 22 20 19 27 23 25 21 21 22 23 25 22 24 23 26 18 21 21
 [2617] 24 25 25 21 26 23 20 20 17 21 23 25 24 21 22 25 23 23 23 26 25 18 22 23
 [2641] 21 20 26 22 23 20 23 22 24 22 24 20 25 25 24 22 22 21 20 19 24 23 21 20
 [2665] 22 23 21 26 24 22 23 25 18 21 24 24 24 25 20 23 22 19 20 24 20 21 24 20
 [2689] 21 20 22 22 23 21 24 20 21 21 20 24 22 22 23 25 22 20 20 22 21 23 21 23
 [2713] 26 22 23 22 22 23 21 21 18 21 24 22 21 25 21 24 25 26 23 16 26 26 20 23
 [2737] 22 28 21 22 22 20 21 22 21 22 22 21 23 22 26 20 17 18 21 19 27 20 20 20
 [2761] 21 25 21 25 28 21 23 23 19 16 23 24 25 19 22 29 17 21 22 24 25 19 21 21
 [2785] 22 21 22 19 21 19 21 21 21 19 19 22 25 26 25 22 18 23 21 23 20 21 22 24
 [2809] 25 21 20 20 24 22 20 23 20 21 24 25 24 21 21 18 19 22 24 20 23 22 19 23
 [2833] 16 19 21 21 21 21 19 23 26 23 19 24 26 22 24 26 26 22 21 18 20 21 21 18
 [2857] 22 26 24 23 19 23 18 25 21 26 18 23 20 20 19 22 24 24 20 24 22 21 23 19
 [2881] 21 24 22 18 18 22 24 20 24 21 21 25 20 22 20 21 24 24 24 23 22 19 22 22
 [2905] 25 20 21 19 24 22 21 20 24 20 23 13 19 22 21 18 24 20 26 21 24 23 25 22
 [2929] 22 24 21 21 25 24 19 24 21 21 23 20 18 21 22 18 21 21 25 24 22 22 24 18
 [2953] 22 24 23 22 23 19 20 20 25 19 20 23 26 28 24 22 25 20 23 23 21 19 22 24
 [2977] 22 21 21 25 26 20 23 20 17 19 20 24 23 22 21 21 20 24 20 17 25 24 20 25
 [3001] 23 21 22 19 24 25 24 21 19 26 17 21 26 22 21 21 23 21 24 23 15 21 22 18
 [3025] 23 24 23 22 21 22 21 19 22 21 25 21 21 23 22 21 26 25 23 22 21 22 19 25
 [3049] 23 20 22 27 20 23 25 21 26 22 22 21 22 27 23 23 24 21 20 21 22 26 23 25
 [3073] 23 22 22 19 25 24 22 26 25 22 24 21 22 21 22 19 24 23 20 25 18 19 22 23
 [3097] 20 19 24 20 26 20 23 24 20 24 22 23 23 19 23 22 20 22 19 22 23 20 20 22
 [3121] 22 24 21 21 21 23 25 22 20 23 20 24 24 23 20 25 24 18 20 24 21 23 19 21
 [3145] 22 23 22 26 22 23 22 20 20 25 23 21 22 21 24 25 24 20 19 21 23 22 23 22
 [3169] 23 23 19 23 24 21 20 23 22 19 20 21 20 20 23 23 23 19 22 23 23 26 25 23
 [3193] 25 21 26 15 25 18 21 21 24 23 20 20 17 23 25 20 19 22 21 21 20 18 21 22
 [3217] 25 26 23 23 24 18 22 23 23 23 22 23 23 25 22 25 24 23 23 26 21 20 16 23
 [3241] 26 22 23 20 19 24 23 23 21 23 20 21 24 22 21 21 22 26 19 21 23 21 19 21
 [3265] 24 26 16 25 18 22 24 23 24 23 19 21 22 24 21 25 19 20 26 17 21 20 20 20
 [3289] 20 23 24 22 20 23 24 26 22 21 25 25 24 19 22 22 19 23 21 23 23 22 18 22
 [3313] 23 23 18 25 24 20 22 17 21 20 22 22 22 23 27 17 20 24 23 19 24 23 24 27
 [3337] 23 22 23 23 21 22 24 23 23 22 26 19 21 20 23 21 24 19 21 25 23 25 19 21
 [3361] 24 22 21 24 31 25 22 21 24 23 24 24 23 24 20 25 26 24 20 22 23 23 19 24
 [3385] 22 25 17 20 25 22 24 23 23 22 22 22 22 19 21 22 24 24 26 21 20 20 24 20
 [3409] 23 22 20 23 21 24 20 22 26 22 22 22 20 21 24 23 26 27 23 26 18 23 21 21
 [3433] 25 24 19 25 25 21 24 22 22 22 24 19 17 20 20 21 23 23 22 23 22 23 22 24
 [3457] 26 23 17 22 22 24 21 23 20 22 16 21 22 21 22 26 19 21 22 18 19 28 26 21
 [3481] 20 20 24 26 25 23 17 19 28 24 20 20 21 23 20 21 27 21 21 18 21 23 21 19
 [3505] 22 25 19 22 22 21 23 18 22 21 20 21 25 25 21 24 20 19 19 25 20 21 23 20
 [3529] 22 21 21 22 22 20 20 22 21 23 22 24 21 21 21 18 20 20 20 21 23 21 18 18
 [3553] 19 19 25 21 21 19 26 21 20 26 24 21 23 20 18 22 21 25 22 20 21 22 21 18
 [3577] 24 21 25 25 24 22 20 21 25 21 23 23 22 25 23 23 19 23 23 20 21 23 19 20
 [3601] 23 24 23 21 24 22 25 25 21 22 19 22 20 19 24 23 23 21 21 22 21 21 26 24
 [3625] 23 21 21 21 27 22 20 25 22 20 26 21 21 19 25 23 18 19 22 22 21 20 24 19
 [3649] 28 22 25 21 21 20 19 22 19 19 21 24 23 21 20 21 22 22 24 21 17 23 23 21
 [3673] 23 23 27 21 22 22 21 23 26 19 22 24 19 21 25 22 21 22 25 26 19 20 19 19
 [3697] 21 18 19 23 23 23 26 23 25 19 20 24 23 22 19 18 20 22 22 20 24 23 19 24
 [3721] 23 25 23 18 25 20 22 22 22 19 24 20 22 19 25 19 20 20 20 25 18 25 24 22
 [3745] 23 19 23 23 19 26 21 21 21 23 22 19 24 24 22 22 21 22 21 21 19 20 23 20
 [3769] 21 20 19 22 21 20 23 17 21 18 18 18 23 20 20 26 22 24 22 20 21 20 22 25
 [3793] 24 22 23 23 21 18 21 23 24 23 20 24 25 20 22 26 18 18 22 20 22 22 21 21
 [3817] 21 23 18 19 23 20 24 26 24 22 20 23 21 22 22 22 19 23 22 21 24 19 24 22
 [3841] 22 22 22 23 20 21 22 26 17 25 22 26 23 23 21 20 19 21 26 24 26 23 23 19
 [3865] 26 24 20 23 21 22 24 21 21 22 24 22 24 24 22 23 23 20 19 23 23 23 25 21
 [3889] 24 19 23 19 22 21 24 26 23 20 17 21 25 22 27 22 26 23 24 23 26 22 21 21
 [3913] 20 20 25 23 24 23 17 26 22 23 22 22 23 24 24 17 23 23 22 22 25 23 23 24
 [3937] 18 27 22 24 24 24 21 18 23 22 22 20 23 21 21 21 26 24 25 18 25 21 26 23
 [3961] 22 21 21 21 27 20 24 22 21 21 22 22 23 20 24 21 25 22 23 25 22 22 20 24
 [3985] 23 26 20 22 20 27 25 26 21 22 19 20 28 22 20 24 20 24 22 20 22 22 20 27
 [4009] 23 23 23 20 19 19 19 21 21 18 23 19 22 25 19 26 21 21 20 23 21 25 21 22
 [4033] 21 21 22 22 21 23 26 23 23 23 29 26 18 24 21 25 20 20 26 25 18 23 25 20
 [4057] 24 22 20 21 23 19 20 23 22 23 24 21 23 23 17 20 21 22 21 26 22 24 21 23
 [4081] 20 24 18 18 24 22 20 24 21 20 24 24 24 22 23 20 19 24 26 20 21 22 24 22
 [4105] 26 25 20 20 25 19 24 24 15 19 26 20 23 26 26 22 25 22 24 23 21 25 20 22
 [4129] 21 22 19 24 22 21 21 19 21 23 22 24 25 23 22 25 18 23 22 23 27 23 27 23
 [4153] 18 22 18 21 22 19 26 21 21 22 21 23 23 21 19 17 21 20 18 22 22 18 20 22
 [4177] 24 21 22 22 21 25 22 23 30 21 22 22 22 18 21 23 20 19 20 22 24 23 22 19
 [4201] 24 16 23 22 21 22 23 22 21 21 24 21 18 21 21 20 24 23 23 25 25 22 17 24
 [4225] 21 21 21 23 20 20 26 21 23 19 21 22 22 24 21 22 22 23 23 22 19 20 27 21
 [4249] 20 26 21 25 23 19 20 20 25 21 21 24 21 22 23 23 18 21 25 18 22 22 24 24
 [4273] 22 23 22 19 23 23 21 20 26 21 19 20 21 25 20 22 26 20 19 22 23 22 18 22
 [4297] 23 21 24 25 23 19 24 22 22 25 25 23 21 23 19 20 26 22 22 19 19 24 21 23
 [4321] 17 21 23 24 20 24 23 23 22 23 21 21 22 20 23 24 25 20 24 21 18 22 21 25
 [4345] 23 20 21 18 21 19 22 17 21 21 24 22 23 21 24 23 19 21 18 24 23 18 20 22
 [4369] 20 24 22 20 22 18 19 22 19 22 24 19 21 25 27 18 21 19 21 25 24 21 23 27
 [4393] 19 23 23 22 21 20 18 19 24 23 19 24 23 23 22 23 20 21 16 22 20 21 23 23
 [4417] 22 26 23 16 24 27 26 19 19 23 22 17 23 22 23 26 25 19 18 23 17 22 25 23
 [4441] 22 23 22 25 21 21 21 22 22 21 23 24 21 19 22 25 25 22 24 19 18 22 16 21
 [4465] 21 24 18 23 20 19 22 21 24 21 21 20 19 23 18 24 22 17 22 23 21 22 22 27
 [4489] 19 19 23 25 21 22 23 27 23 26 25 24 21 26 24 22 20 23 25 23 22 23 23 22
 [4513] 22 22 23 23 21 22 18 23 23 19 24 18 27 24 28 21 21 25 20 18 25 20 23 20
 [4537] 25 24 25 21 21 23 18 20 21 23 18 24 23 20 24 25 24 23 21 23 23 23 19 24
 [4561] 23 20 21 22 20 21 22 21 22 23 23 20 23 20 23 20 25 18 24 24 20 23 23 19
 [4585] 23 26 20 22 27 24 22 25 24 23 23 21 20 21 24 25 21 20 21 20 19 22 25 24
 [4609] 22 23 19 21 22 24 21 20 23 21 20 21 24 25 21 22 24 19 25 24 18 19 23 23
 [4633] 25 24 21 20 19 26 21 21 22 27 21 24 24 19 23 25 19 23 22 19 23 16 21 20
 [4657] 24 26 23 23 23 17 23 21 18 24 15 23 25 22 25 21 26 22 23 26 23 25 22 21
 [4681] 25 20 22 21 23 22 19 22 21 23 24 19 25 26 23 23 24 23 18 19 22 22 24 22
 [4705] 24 22 21 23 23 23 21 22 20 25 24 21 21 22 22 23 24 20 25 23 20 24 24 21
 [4729] 24 21 22 20 20 20 22 21 19 18 23 26 21 21 20 23 24 25 17 18 19 22 25 21
 [4753] 21 28 18 25 18 25 22 24 23 24 21 22 22 21 22 19 26 18 27 23 24 22 20 23
 [4777] 21 24 23 27 22 22 22 19 22 21 24 22 20 23 21 22 19 20 24 22 22 24 23 26
 [4801] 20 21 20 24 22 25 23 22 22 23 21 27 22 21 16 26 25 23 24 23 22 24 19 24
 [4825] 22 20 21 22 23 22 25 20 22 23 21 21 22 21 19 23 19 26 21 22 23 20 21 19
 [4849] 21 23 24 27 27 20 21 25 25 18 20 22 22 25 19 21 20 20 22 23 25 23 22 22
 [4873] 24 22 25 21 19 25 20 24 23 24 26 26 22 19 23 20 21 23 23 25 19 24 22 23
 [4897] 21 17 22 19 22 24 25 19 23 26 21 25 22 22 26 25 21 26 25 25 25 23 21 26
 [4921] 20 21 24 21 19 18 25 28 22 25 20 21 23 25 24 23 20 23 24 19 21 23 20 25
 [4945] 19 20 25 22 22 21 23 22 24 22 23 20 24 23 24 23 23 22 22 21 25 19 26 23
 [4969] 17 24 17 23 22 24 23 24 20 23 19 23 16 28 23 23 19 18 21 22 19 19 21 18
 [4993] 22 23 24 19 23 19 24 28 23 24 23 21 25 26 25 23 21 25 17 18 23 21 24 21
 [5017] 20 19 24 22 22 23 21 24 21 22 22 19 19 20 22 23 21 23 22 25 23 23 21 19
 [5041] 20 24 25 18 24 21 22 19 24 25 23 24 20 22 22 22 23 22 21 21 20 21 21 22
 [5065] 23 20 21 21 24 20 21 24 24 20 20 19 20 17 24 18 22 22 21 24 26 21 25 18
 [5089] 22 24 24 28 18 21 22 19 22 20 23 22 21 23 22 23 24 20 26 22 23 21 18 23
 [5113] 24 23 18 20 19 20 24 24 21 25 25 21 20 20 23 25 20 21 22 24 21 22 26 22
 [5137] 23 23 20 22 24 23 20 20 24 26 25 22 22 21 22 25 19 17 16 20 21 22 20 25
 [5161] 19 21 24 20 20 23 25 20 20 26 22 18 23 20 27 20 22 20 22 22 21 22 22 27
 [5185] 22 21 23 20 24 25 22 19 21 22 18 23 23 22 21 20 25 20 22 22 21 20 20 24
 [5209] 21 19 25 21 24 25 21 23 22 22 20 23 27 26 19 21 19 20 19 25 22 22 24 24
 [5233] 26 22 21 20 26 22 27 25 22 24 19 25 24 24 22 20 19 23 22 20 24 19 21 25
 [5257] 21 24 20 22 25 25 23 20 18 22 22 24 22 20 19 21 26 20 25 23 23 20 25 27
 [5281] 28 23 25 22 20 22 23 21 21 23 24 28 20 21 23 18 21 21 21 22 24 22 24 21
 [5305] 24 20 25 22 19 23 22 24 21 22 18 21 21 18 22 19 22 20 21 23 19 21 22 23
 [5329] 20 22 21 25 25 18 22 21 20 18 22 20 21 18 24 17 23 23 23 23 21 25 19 21
 [5353] 22 25 21 20 25 23 23 22 26 18 22 21 23 19 18 17 20 22 25 23 24 23 22 22
 [5377] 25 18 27 22 18 21 21 23 23 23 21 20 21 21 22 19 20 23 18 20 22 23 18 21
 [5401] 21 22 20 23 20 26 18 23 25 24 22 25 24 25 25 24 19 24 21 19 19 26 16 24
 [5425] 19 25 22 23 23 20 20 24 20 20 20 22 23 19 21 20 21 24 26 22 23 23 22 22
 [5449] 23 24 19 20 21 22 23 27 19 23 23 25 23 25 22 21 20 20 23 20 24 21 25 25
 [5473] 20 21 23 25 20 21 24 22 18 23 21 25 23 24 24 22 21 24 25 22 24 25 23 21
 [5497] 22 22 23 22 21 23 21 22 24 24 23 21 21 22 23 23 24 24 26 22 22 21 28 19
 [5521] 18 25 17 22 22 23 23 19 19 22 29 20 23 22 23 18 24 20 23 23 21 17 19 23
 [5545] 16 20 22 20 22 19 21 22 26 26 25 20 19 22 22 19 22 27 21 22 25 17 23 20
 [5569] 25 23 20 19 23 21 21 21 26 21 21 24 21 20 20 21 24 22 22 21 22 20 17 22
 [5593] 25 22 25 22 18 25 22 22 20 23 23 23 16 24 20 22 22 21 22 26 19 19 24 22
 [5617] 23 23 27 23 25 25 21 23 19 22 25 21 24 23 21 18 22 25 18 21 23 25 26 23
 [5641] 17 22 21 19 26 20 23 22 21 24 21 21 23 21 23 22 23 22 25 19 23 21 25 21
 [5665] 22 22 20 22 23 23 23 24 23 25 24 23 22 21 22 21 22 21 19 21 19 22 22 28
 [5689] 24 23 22 23 23 24 24 24 23 21 22 21 27 23 25 24 20 20 23 27 21 22 21 22
 [5713] 24 21 23 26 23 20 24 20 21 22 21 22 24 23 22 23 22 24 22 24 20 20 20 23
 [5737] 24 18 22 24 16 21 20 22 21 24 26 23 18 25 23 23 21 21 20 17 20 20 25 21
 [5761] 22 21 21 19 25 24 18 23 22 22 25 22 24 23 21 23 21 22 21 24 20 22 24 21
 [5785] 18 20 26 28 24 22 23 22 19 23 21 24 25 18 23 24 21 23 21 23 21 19 23 21
 [5809] 24 23 18 24 28 21 26 24 22 25 27 23 21 25 22 17 23 18 26 22 21 22 24 23
 [5833] 22 24 21 20 24 20 18 20 23 19 20 22 20 21 23 15 19 22 21 19 25 22 22 22
 [5857] 24 22 20 21 21 21 19 26 22 20 24 18 24 24 20 19 20 19 23 23 22 23 20 26
 [5881] 24 23 23 23 21 21 25 24 22 25 23 17 21 18 20 24 19 28 23 22 22 21 19 23
 [5905] 22 20 24 22 26 23 22 21 24 23 24 23 24 16 20 21 24 21 20 22 23 17 26 20
 [5929] 20 24 23 19 22 26 27 26 24 22 22 25 25 22 21 19 18 13 24 22 20 22 23 24
 [5953] 21 19 23 26 21 27 25 21 22 21 17 23 20 28 23 22 18 19 18 19 19 24 21 21
 [5977] 23 22 23 21 23 20 20 22 21 20 24 23 22 29 20 23 22 19 23 23 24 22 20 23
 [6001] 20 22 20 25 24 15 21 22 24 22 22 21 23 22 22 19 22 19 25 21 18 22 25 24
 [6025] 24 22 22 25 27 23 29 23 24 20 26 20 21 21 23 22 24 23 24 20 23 26 22 20
 [6049] 23 21 22 20 23 20 21 19 22 21 23 19 24 24 23 21 19 27 22 21 20 21 22 22
 [6073] 20 21 20 20 21 25 24 26 22 21 23 19 22 24 23 24 23 22 20 25 23 22 21 19
 [6097] 22 21 20 22 23 23 25 25 22 21 26 24 21 20 19 24 16 23 23 23 20 22 21 24
 [6121] 20 23 23 17 25 19 20 23 24 20 26 22 23 26 22 20 26 18 21 19 16 21 21 24
 [6145] 22 24 25 25 21 17 20 22 21 18 17 23 18 19 22 20 18 24 19 23 22 27 19 23
 [6169] 22 21 22 21 21 23 21 22 24 21 20 21 26 22 25 26 21 22 25 23 21 24 20 19
 [6193] 23 26 16 19 21 21 22 23 21 21 18 21 20 22 20 22 19 26 26 19 25 23 23 24
 [6217] 25 23 27 24 23 27 25 25 14 19 23 23 22 21 22 21 22 21 24 21 24 22 22 20
 [6241] 21 22 25 22 21 22 22 23 25 20 23 22 28 20 19 21 22 25 19 22 21 22 22 27
 [6265] 23 18 20 25 20 24 21 21 26 21 23 24 24 22 24 20 22 21 24 20 25 23 24 21
 [6289] 24 20 20 21 21 20 27 21 21 23 22 25 22 18 22 22 23 23 27 19 23 23 21 19
 [6313] 24 22 26 24 20 22 24 24 23 22 21 19 23 22 20 21 25 22 21 25 21 26 22 24
 [6337] 25 28 24 21 23 21 20 24 19 19 20 22 21 18 20 24 27 23 24 25 27 20 19 22
 [6361] 19 21 24 17 25 25 24 23 22 26 24 18 25 20 18 25 23 23 25 22 23 24 22 22
 [6385] 24 20 26 22 25 25 21 24 21 25 19 22 22 23 24 25 21 26 19 27 25 23 19 21
 [6409] 24 23 24 22 24 19 22 24 25 19 22 23 25 26 19 26 21 23 17 20 21 23 23 23
 [6433] 23 23 23 21 21 23 23 19 22 24 27 23 20 26 22 22 21 28 21 21 21 22 24 20
 [6457] 24 23 24 20 25 23 21 26 24 22 20 22 20 20 23 21 23 17 20 21 21 23 23 17
 [6481] 22 25 22 24 25 17 24 23 21 18 21 20 23 21 22 21 21 20 19 21 22 22 22 23
 [6505] 22 19 24 27 24 22 25 19 22 27 22 14 22 17 20 22 22 18 25 21 24 19 22 24
 [6529] 20 25 21 19 21 22 19 22 21 22 25 16 22 24 23 21 21 23 21 23 20 19 20 22
 [6553] 21 21 19 23 24 23 23 22 20 21 22 19 20 23 22 22 23 21 26 17 22 21 24 23
 [6577] 27 21 24 21 21 21 19 21 21 21 20 23 25 21 26 27 21 21 26 20 22 18 18 19
 [6601] 23 22 24 24 21 20 22 22 21 20 18 26 22 23 21 25 24 21 22 23 19 24 22 25
 [6625] 25 27 23 19 24 23 26 24 24 21 23 24 24 21 23 23 21 24 22 18 23 19 21 21
 [6649] 19 25 25 22 24 20 21 20 20 21 23 21 21 23 19 21 28 19 23 22 24 17 24 22
 [6673] 24 21 22 19 24 20 21 22 20 26 22 25 20 24 28 25 20 20 23 27 23 22 16 26
 [6697] 24 20 20 23 23 20 23 23 22 21 21 23 21 22 21 26 24 22 26 26 21 24 24 28
 [6721] 20 18 23 21 20 19 24 17 18 20 21 24 18 22 16 21 22 23 23 23 23 20 20 23
 [6745] 26 20 22 24 20 23 24 24 26 25 22 22 16 22 24 24 22 25 23 23 22 23 20 23
 [6769] 26 26 21 24 22 18 21 19 25 22 21 19 24 25 23 19 19 18 22 22 23 19 20 22
 [6793] 23 21 22 23 25 23 30 21 21 23 24 24 24 23 23 24 20 22 24 24 23 21 19 23
 [6817] 23 22 21 28 24 22 23 23 17 23 28 23 24 22 25 25 18 25 20 22 20 25 22 24
 [6841] 23 21 22 19 26 24 25 22 22 21 23 21 23 23 20 26 20 24 19 21 20 20 18 26
 [6865] 22 22 20 24 26 23 23 24 21 20 24 20 24 21 23 24 17 20 26 24 20 19 20 19
 [6889] 22 27 22 16 24 23 22 23 23 23 22 25 24 26 21 22 21 21 21 24 25 23 20 19
 [6913] 23 26 25 23 22 20 24 25 21 20 20 26 25 22 23 22 20 24 20 19 23 21 17 23
 [6937] 19 20 25 25 20 24 25 22 20 22 23 19 23 22 20 21 23 25 22 22 24 21 26 21
 [6961] 23 18 21 26 23 16 20 23 25 22 20 22 24 25 22 17 24 23 24 21 27 20 23 22
 [6985] 21 21 21 24 25 24 25 22 19 21 19 25 20 17 22 24 21 22 23 20 18 20 21 22
 [7009] 19 24 20 19 22 22 18 23 27 27 20 23 25 22 23 20 22 21 18 26 21 19 24 24
 [7033] 23 23 20 25 20 21 25 22 21 20 22 21 23 27 21 27 22 26 22 25 23 21 20 23
 [7057] 21 23 17 24 19 20 24 24 23 28 22 26 22 21 23 22 23 20 23 18 19 21 20 23
 [7081] 22 22 19 21 23 20 25 21 22 23 19 20 23 27 22 20 25 20 20 22 25 25 21 18
 [7105] 20 22 21 25 22 20 20 28 22 24 22 24 23 24 18 26 25 22 20 26 21 25 26 24
 [7129] 23 22 22 20 19 25 21 21 22 21 25 22 25 23 24 21 20 18 22 20 22 22 22 22
 [7153] 19 25 21 24 20 26 23 24 24 22 19 21 24 22 25 22 23 22 22 24 22 21 25 19
 [7177] 22 23 26 18 26 21 20 26 22 20 25 24 24 21 22 20 20 26 19 21 19 21 23 21
 [7201] 18 23 20 26 21 21 26 24 22 25 23 21 24 24 20 19 23 21 20 23 20 23 22 24
 [7225] 17 21 20 23 23 21 23 21 20 21 17 20 23 25 23 22 19 17 18 22 22 20 24 22
 [7249] 21 23 17 18 23 22 19 20 23 19 26 18 23 20 24 17 22 25 20 24 28 19 22 19
 [7273] 22 27 24 19 22 24 20 21 20 20 20 23 27 23 22 21 26 19 22 23 20 26 23 22
 [7297] 19 21 19 21 22 18 28 23 18 26 20 23 22 20 17 23 23 22 24 21 25 25 20 22
 [7321] 22 21 23 20 25 22 18 20 29 23 19 21 22 29 23 22 22 21 23 19 22 23 23 22
 [7345] 15 25 21 24 21 25 22 22 27 19 20 21 21 22 19 20 24 25 21 18 25 23 23 20
 [7369] 19 22 25 23 22 17 20 18 22 23 22 24 21 22 22 19 21 22 20 25 21 21 22 21
 [7393] 23 23 23 23 23 23 18 22 23 23 21 20 22 23 20 19 25 22 18 19 23 23 22 21
 [7417] 18 26 20 17 21 20 22 25 26 18 18 22 24 19 27 18 26 24 22 19 22 26 25 20
 [7441] 20 22 24 19 21 21 20 20 22 21 19 20 18 24 20 24 23 19 22 19 24 23 20 21
 [7465] 23 23 22 23 22 17 28 28 24 25 24 17 27 27 22 25 20 24 23 23 22 26 20 19
 [7489] 21 20 24 20 26 23 23 23 20 23 25 25 25 22 19 24 21 20 24 22 19 23 18 19
 [7513] 26 24 24 25 23 20 20 20 18 26 22 20 19 24 23 19 23 18 24 27 24 29 20 22
 [7537] 24 22 18 23 25 24 23 21 19 23 25 25 24 23 21 21 23 22 20 24 25 21 16 21
 [7561] 21 25 22 24 20 23 22 18 20 22 20 25 21 22 26 23 24 25 19 22 21 24 20 27
 [7585] 22 24 23 19 23 23 26 21 25 23 19 23 20 22 18 22 20 22 23 19 21 24 22 25
 [7609] 22 20 20 20 21 21 23 23 25 21 21 21 23 21 19 24 21 18 20 22 23 21 24 24
 [7633] 21 20 22 23 18 23 26 20 22 26 23 21 20 19 26 22 20 23 22 22 20 18 23 20
 [7657] 19 20 25 25 22 23 22 25 23 21 24 18 23 23 24 23 20 21 19 22 24 21 23 19
 [7681] 21 28 22 22 22 25 20 22 19 23 22 26 24 22 19 18 22 22 23 18 22 21 21 24
 [7705] 22 21 24 24 22 25 23 26 25 22 19 23 25 21 21 17 17 23 19 23 25 22 23 23
 [7729] 20 21 24 22 21 22 21 20 21 22 19 23 23 20 22 22 20 22 21 21 20 23 25 24
 [7753] 21 20 21 23 21 23 19 21 21 26 23 28 24 21 24 19 20 24 24 20 19 23 20 21
 [7777] 23 25 23 25 20 22 20 21 24 24 25 20 21 22 21 22 20 23 20 22 21 22 24 22
 [7801] 25 23 21 22 23 25 21 20 20 25 22 23 21 20 19 23 22 19 25 22 19 22 16 20
 [7825] 25 24 20 20 25 20 22 22 24 23 22 27 25 16 18 21 21 19 22 19 20 23 18 23
 [7849] 26 24 24 20 24 23 17 25 19 18 23 19 25 21 22 25 25 22 25 18 19 23 19 23
 [7873] 27 22 20 19 24 20 24 23 23 20 24 23 20 23 22 22 22 24 20 21 22 21 23 19
 [7897] 24 21 19 23 26 23 21 21 22 21 21 21 20 22 23 19 26 20 23 23 22 23 20 20
 [7921] 24 21 21 23 23 24 23 25 22 21 26 22 25 23 21 24 18 26 20 18 27 24 21 23
 [7945] 22 23 22 21 23 18 26 23 24 24 23 21 28 21 27 23 23 23 22 26 22 22 22 22
 [7969] 20 21 23 22 25 23 21 22 19 18 18 19 25 21 19 22 23 23 23 22 20 23 21 27
 [7993] 18 26 17 21 23 23 21 23 17 23 22 21 22 22 24 25 26 22 24 25 21 25 27 24
 [8017] 23 23 20 23 22 25 24 24 19 21 24 19 24 20 22 23 25 20 20 23 20 22 19 25
 [8041] 21 22 21 21 21 22 22 24 20 25 23 24 24 22 19 22 20 23 25 20 23 23 19 17
 [8065] 17 21 22 22 25 22 24 23 25 25 25 25 20 18 19 22 24 25 23 21 21 23 22 22
 [8089] 22 25 21 22 23 23 18 20 22 26 23 26 20 22 19 19 25 26 25 23 23 21 23 22
 [8113] 19 21 22 25 19 28 21 19 19 22 25 26 23 22 25 22 22 26 24 23 23 26 26 22
 [8137] 22 20 22 24 22 18 22 19 20 23 21 21 18 23 23 21 22 23 19 20 23 22 23 21
 [8161] 24 21 19 24 27 19 20 23 23 20 20 24 24 25 20 22 25 18 20 19 19 24 21 23
 [8185] 21 22 21 20 22 23 22 20 21 22 22 18 24 23 25 21 23 22 18 17 20 22 23 21
 [8209] 18 19 21 24 26 19 20 25 25 23 23 22 20 19 20 27 19 16 23 22 23 24 26 21
 [8233] 16 20 21 22 21 21 26 23 21 20 25 24 21 22 25 21 23 23 17 22 21 24 21 24
 [8257] 24 20 25 21 19 21 23 24 23 20 24 27 22 19 20 28 22 24 22 25 21 21 24 21
 [8281] 28 23 22 23 19 22 25 23 24 22 24 23 21 22 20 22 21 25 20 24 25 21 26 24
 [8305] 24 21 21 18 24 26 23 24 22 21 21 21 17 21 27 21 24 21 23 18 16 24 21 21
 [8329] 21 22 23 21 23 23 22 24 21 25 21 19 22 23 18 22 22 22 20 22 26 22 20 18
 [8353] 22 25 27 22 19 20 25 22 25 24 22 22 22 24 24 24 23 24 21 19 28 24 20 23
 [8377] 21 20 21 26 26 22 24 23 24 19 25 20 22 21 20 17 27 23 20 21 23 21 19 22
 [8401] 27 19 23 23 23 25 24 23 24 23 20 23 25 26 22 25 20 25 24 23 21 23 23 26
 [8425] 22 21 24 24 19 20 28 24 23 20 20 25 24 19 22 23 20 23 22 17 24 26 23 23
 [8449] 20 20 22 23 24 21 26 25 21 23 20 22 23 23 23 24 22 26 24 21 18 24 23 24
 [8473] 22 16 22 18 21 20 23 18 25 22 21 22 22 21 25 20 21 27 21 21 22 23 23 18
 [8497] 16 21 27 27 22 19 29 21 22 18 25 25 22 18 21 27 18 21 24 23 21 23 21 20
 [8521] 20 24 24 24 26 21 20 22 24 27 18 18 24 26 20 27 21 21 20 24 24 23 21 23
 [8545] 23 23 20 22 20 28 20 21 22 27 27 26 22 23 21 19 24 19 24 23 21 19 22 23
 [8569] 24 23 23 23 25 23 21 22 20 19 22 21 22 24 23 23 21 25 24 21 23 21 23 20
 [8593] 16 22 24 26 22 22 19 22 19 22 22 23 23 28 19 22 28 25 19 25 18 26 23 24
 [8617] 23 21 22 23 20 23 22 20 21 22 16 24 21 24 20 25 20 26 19 26 22 23 22 23
 [8641] 19 23 23 24 23 25 24 24 21 23 25 22 21 21 21 23 25 23 21 19 17 21 19 24
 [8665] 21 20 22 22 22 24 18 19 23 16 24 22 22 20 20 20 20 21 20 21 24 22 22 20
 [8689] 27 21 21 23 24 22 23 25 21 24 25 23 24 23 19 21 26 22 25 27 19 22 21 21
 [8713] 26 24 23 18 19 25 24 24 23 23 21 20 20 24 22 24 21 21 23 22 24 26 21 19
 [8737] 21 22 27 23 22 19 19 25 18 25 22 23 19 23 20 19 23 23 24 21 20 26 23 23
 [8761] 22 22 24 23 20 21 24 22 20 21 20 18 24 23 22 23 19 23 26 24 21 21 26 24
 [8785] 20 22 26 23 20 24 19 22 22 17 23 23 24 21 23 21 21 19 18 20 22 20 23 22
 [8809] 22 21 23 23 26 21 25 21 22 23 24 20 24 23 23 26 24 26 24 20 22 22 25 24
 [8833] 20 23 22 24 22 22 22 21 20 26 20 24 22 24 23 23 22 23 23 23 24 24 18 24
 [8857] 21 24 21 17 22 26 24 21 21 20 21 25 21 21 19 18 17 21 21 22 21 19 22 23
 [8881] 20 22 21 25 18 20 25 24 21 21 23 25 19 24 23 20 17 25 19 21 21 22 19 24
 [8905] 23 23 24 18 22 22 20 22 26 26 18 19 21 22 22 21 21 21 23 23 21 23 23 18
 [8929] 22 21 24 22 25 20 22 22 22 21 17 21 19 18 23 23 18 21 19 18 22 23 20 23
 [8953] 23 23 24 23 22 22 21 23 22 25 19 22 19 19 21 21 23 26 22 21 24 25 21 21
 [8977] 23 20 27 21 25 27 26 26 24 20 23 22 28 26 22 23 21 21 19 19 23 20 26 22
 [9001] 21 23 21 19 22 24 21 23 23 20 21 26 21 24 22 20 18 19 20 21 22 21 23 20
 [9025] 20 21 21 21 24 24 25 24 22 22 22 21 24 22 20 22 23 21 22 20 19 22 19 20
 [9049] 23 20 18 28 24 25 16 23 23 24 25 18 22 20 23 20 22 21 22 21 21 21 24 25
 [9073] 21 21 21 21 25 27 24 21 23 18 23 24 21 20 25 22 23 17 20 24 17 24 25 22
 [9097] 19 23 20 23 20 19 23 23 22 22 20 24 24 21 24 24 26 18 20 19 21 21 25 20
 [9121] 19 18 20 23 23 26 20 21 24 18 20 22 18 22 20 15 20 22 20 20 23 20 23 24
 [9145] 25 23 25 22 20 24 23 22 23 21 29 20 21 20 20 19 28 18 26 20 21 21 21 21
 [9169] 25 18 17 23 20 24 22 22 23 19 20 23 25 23 23 24 19 20 18 22 22 22 22 24
 [9193] 22 22 23 21 24 22 25 25 19 24 24 18 23 21 20 22 22 22 21 20 25 21 25 25
 [9217] 20 22 16 23 22 22 21 22 24 20 23 20 21 26 23 26 24 22 22 25 20 20 26 21
 [9241] 23 25 21 21 25 17 26 20 21 23 23 24 27 24 26 20 19 24 18 20 22 20 20 27
 [9265] 21 20 25 24 22 21 25 22 17 24 21 24 23 27 18 27 19 22 24 22 23 26 26 19
 [9289] 23 19 19 21 21 24 19 22 24 26 24 27 23 24 24 18 20 23 21 24 22 22 22 24
 [9313] 17 19 23 22 21 23 19 25 20 25 19 20 24 21 22 25 27 19 22 26 24 27 21 22
 [9337] 21 20 25 18 20 18 20 17 21 21 24 25 24 22 19 24 21 23 21 17 19 25 24 19
 [9361] 19 18 20 18 21 20 26 22 21 24 22 20 21 18 22 18 22 21 19 22 25 22 24 17
 [9385] 26 20 22 23 22 20 18 21 23 17 23 18 17 22 24 18 21 24 26 27 24 20 19 18
 [9409] 22 20 16 22 20 17 25 23 21 19 23 24 24 26 20 20 17 20 19 18 23 24 25 16
 [9433] 21 22 22 21 19 21 24 23 22 26 23 23 24 21 20 21 18 20 20 25 17 21 22 20
 [9457] 20 19 25 24 22 22 25 19 17 24 24 22 21 23 27 19 23 24 21 19 22 19 22 21
 [9481] 25 25 23 22 22 24 23 25 23 17 19 20 22 22 25 19 20 22 20 19 22 28 20 26
 [9505] 25 21 23 23 22 22 23 23 23 20 24 19 23 23 22 23 23 21 18 21 17 22 23 25
 [9529] 21 22 20 24 21 24 27 19 20 22 23 18 22 22 20 23 28 24 19 20 23 27 27 23
 [9553] 21 20 26 18 21 20 24 18 19 23 22 19 23 20 19 24 23 24 22 20 27 18 22 24
 [9577] 21 16 24 20 25 23 23 19 22 22 24 24 26 25 25 22 23 22 21 20 26 23 19 21
 [9601] 22 24 25 20 26 20 26 21 17 20 19 21 25 23 23 25 22 23 21 19 23 22 21 19
 [9625] 20 22 22 20 24 21 29 20 24 23 22 23 22 18 20 20 23 22 24 21 26 22 19 19
 [9649] 19 22 23 21 24 21 23 21 23 23 21 21 22 23 23 25 23 23 23 18 20 19 23 23
 [9673] 24 24 23 18 23 22 21 28 24 23 18 16 18 18 19 23 23 22 26 25 24 24 22 20
 [9697] 25 24 21 21 20 19 28 23 18 24 23 24 22 23 23 24 25 20 22 21 17 21 21 23
 [9721] 19 20 27 23 25 22 20 21 24 23 26 18 27 24 25 20 27 21 21 20 23 22 23 19
 [9745] 22 22 21 23 19 26 21 21 23 17 21 21 21 23 24 25 20 24 20 25 20 20 22 25
 [9769] 22 24 21 24 21 20 19 19 21 22 19 25 26 20 23 20 19 25 24 20 22 21 25 24
 [9793] 22 22 23 24 20 18 23 26 24 22 23 23 22 20 27 23 22 20 21 20 22 19 21 19
 [9817] 20 25 22 23 21 22 23 21 23 19 23 20 25 23 21 20 19 20 20 20 25 23 21 24
 [9841] 23 23 27 23 23 24 17 22 22 22 21 24 22 16 22 23 22 21 20 18 26 24 19 23
 [9865] 21 18 22 21 23 19 20 19 24 20 22 26 18 19 23 20 20 25 19 22 24 21 22 20
 [9889] 20 24 23 19 21 24 23 21 22 22 22 21 21 25 23 21 22 21 24 18 20 20 22 25
 [9913] 24 19 21 22 26 20 21 23 21 22 23 24 25 24 23 23 23 20 21 21 23 24 22 21
 [9937] 18 19 24 24 25 24 20 24 25 20 18 24 23 20 24 21 24 18 23 19 21 23 23 20
 [9961] 23 22 22 21 20 18 22 24 17 25 23 20 25 24 22 19 23 24 18 22 22 24 23 23
 [9985] 22 19 23 20 21 25 22 21 23 23 19 20 22 22 22 21

matrix_3_df <- as.data.frame(matrix_3)

histogram_BCN_one_to_one_orthologs_skogs <- ggplot(matrix_3_df, aes(x=matrix_3))+ geom_histogram(binwidth=0.5, alpha=0.4)

#determine the total number of unique modules the randomized set of Skogsbergia sp. transcripts are found in. 
table(matrix_3_df)

matrix_3_df
  13   14   15   16   17   18   19   20   21   22   23   24   25   26   27   28 
   2    6   12   56  150  385  725 1196 1529 1676 1623 1172  779  431  168   69 
  29   30   31 
  17    3    1

histogram_BCN_one_to_one_orthologs_skogs_prettyversion <- 
ggplot(matrix_3_df, aes(x=matrix_3)) +#+ theme_classic()+
labs(x="Skogsbergia sp Modules", y = "Count") +
geom_histogram(color ="darkblue", fill="lightblue", size=1, bins=16)+ scale_x_continuous(breaks = seq(min(matrix_3_df$matrix_3), max(matrix_3_df$matrix_3)))+
theme(text=element_text(family = "Arial")) +
theme(axis.title.x = element_text(size = 20)) +     
theme(axis.title.y = element_text(size = 20))  +
 theme(axis.text.x = element_text(size = 15)) +
theme(axis.text.y = element_text(size = 15)) +
geom_vline(data=matrix_3_df, aes(xintercept=24, color="black"),
             linetype="dashed", size =1)+labs(color = "") +
theme(legend.position = "none")

histogram_BCN_one_to_one_orthologs_skogs_prettyversion

References

P. Langfelder, S. Horvath, WGCNA: an R package for weighted correlation network analysis. BMC Bioinformatics 9, 559 (2008)

M. I. Love, W. Huber, S. Anders, Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15, 550 (2014)

Alexa A, Rahnenfuhrer J, topGO: Enrichment Analysis for Gene Ontology (2024)

Shannon, Paul et al., Cytoscape: a software environment for integrated models of biomolecular interaction networks. Genome research vol. 13,11 (2003)

	Sk.10A_fasta90_isoform.counts.tab	Sk.10B_fasta90_isoform.counts.tab	Sk.10C_fasta90_isoform.counts.tab	Sk.6A_fasta90_isoform.counts.tab	Sk.6B_fasta90_isoform.counts.tab	Sk.6C_fasta90_isoform..counts.tab	Sk.7A_fasta90_isoform.counts.tab	Sk.7B_fasta90_isoform.counts.tab	Sk.7C_fasta90_isoform.counts.tab	Sk.8A_fasta90_isoform.counts.tab	Sk.8B_fasta90_isoform..counts.tab	Sk.8C_fasta90_isoform..counts.tab	Sk.9A_fasta90_isoform.counts.tab	Sk.9B_fasta90_isoform..counts.tab	Sk.9C_fasta90_isoform.counts.tab
	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>	<int>
TRINITY_DN0_c0_g1_i2	0	14	570	0	1	755	15	3	201	13	27	141	5	5	533
TRINITY_DN0_c0_g3_i1	6	1	68	6	18	195	13	2	32	6	3	31	3	0	68
TRINITY_DN0_c0_g4_i2	2	26	928	9	0	1699	32	13	684	74	194	506	13	97	1367
TRINITY_DN100000_c0_g1_i1	0	0	0	0	0	0	3	1	1	8	0	6	0	0	0
TRINITY_DN100005_c0_g1_i1	7	5	10	0	4	6	10	2	5	6	1	10	5	10	7
TRINITY_DN100007_c0_g1_i1	0	0	4	4	0	4	1	0	9	0	4	7	4	0	3

transcript_id	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN100127_c0_g1_i1	3.608228	4.480129	1.0997747	4.013424	5.984419e-05	0.007626394
TRINITY_DN10153_c1_g1_i1	47.303025	-1.928367	0.5315456	-3.618480	2.963379e-04	0.023914234
TRINITY_DN1015_c0_g1_i4	23.418584	-6.401983	1.4252019	-3.850651	1.178042e-04	0.012554149
TRINITY_DN101713_c0_g1_i1	9.193390	3.706762	0.8953110	3.997082	6.412797e-05	0.008066841
TRINITY_DN10186_c1_g1_i1	4.266713	-4.489130	1.2628190	-3.476959	5.071345e-04	0.035493613
TRINITY_DN10190_c0_g1_i1	3.596375	3.404744	1.0077576	3.406440	6.581610e-04	0.042200953

#gene_id	transcript_id	sprot_Top_BLASTX_hit	RNAMMER	prot_id	prot_coords	sprot_Top_BLASTP_hit	Pfam	SignalP	TmHMM	⋯	gene_ontology_BLASTP	gene_ontology_Pfam	transcript	peptide	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	⋯	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN100127_c0_g1	TRINITY_DN100127_c0_g1_i1	.	.	TRINITY_DN100127_c0_g1_i1.p1	7-969[-]	.	.	sigP:1^18^0.696	.	⋯	.	.	.	.	3.608228	4.480129	1.0997747	4.013424	5.984419e-05	0.007626394
TRINITY_DN101713_c0_g1	TRINITY_DN101713_c0_g1_i1	CIB3_HUMAN^CIB3_HUMAN^Q:51-617,H:1-187^51.323%ID^E:4.54e-65^RecName: Full=Calcium and integrin-binding family member 3;^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia; Eutheria; Euarchontoglires; Primates; Haplorrhini; Catarrhini; Hominidae; Homo	.	TRINITY_DN101713_c0_g1_i1.p1	3-620[+]	CIB3_HUMAN^CIB3_HUMAN^Q:17-205,H:1-187^51.323%ID^E:3.41e-65^RecName: Full=Calcium and integrin-binding family member 3;^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia; Eutheria; Euarchontoglires; Primates; Haplorrhini; Catarrhini; Hominidae; Homo	PF13499.9^EF-hand_7^EF-hand domain pair^127-191^E:4.1e-11	.	.	⋯	GO:0005509^molecular_function^calcium ion binding`GO:0000287^molecular_function^magnesium ion binding	GO:0005509^molecular_function^calcium ion binding	.	.	9.193390	3.706762	0.8953110	3.997082	6.412797e-05	0.008066841
TRINITY_DN10190_c0_g1	TRINITY_DN10190_c0_g1_i1	.	.	TRINITY_DN10190_c0_g1_i1.p2	3-323[-]	.	.	.	.	⋯	.	.	.	.	3.596375	3.404744	1.0077576	3.406440	6.581610e-04	0.042200953
TRINITY_DN101_c0_g1	TRINITY_DN101_c0_g1_i6	.	.	.	.	.	.	.	.	⋯	.	.	.	.	2916.039845	3.000134	0.8203465	3.619463	2.952156e-04	0.023914234
TRINITY_DN101_c0_g4	TRINITY_DN101_c0_g4_i1	.	.	.	.	.	.	.	.	⋯	.	.	.	.	389.650351	2.999287	0.6984127	4.269612	1.958133e-05	0.003016171
TRINITY_DN10265_c0_g2	TRINITY_DN10265_c0_g2_i1	OTUBL_DROME^OTUBL_DROME^Q:19-780,H:1-261^53.64%ID^E:1.15e-94^RecName: Full=Ubiquitin thioesterase otubain-like;^Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota; Neoptera; Endopterygota; Diptera; Brachycera; Muscomorpha; Ephydroidea; Drosophilidae; Drosophila; Sophophora	.	TRINITY_DN10265_c0_g2_i1.p1	19-783[+]	OTUBL_DROME^OTUBL_DROME^Q:1-254,H:1-261^53.64%ID^E:7.52e-99^RecName: Full=Ubiquitin thioesterase otubain-like;^Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota; Neoptera; Endopterygota; Diptera; Brachycera; Muscomorpha; Ephydroidea; Drosophilidae; Drosophila; Sophophora	PF10275.12^Peptidase_C65^Peptidase C65 Otubain^27-254^E:1.3e-77	.	.	⋯	GO:0005634^cellular_component^nucleus`GO:0004843^molecular_function^cysteine-type deubiquitinase activity`GO:0043130^molecular_function^ubiquitin binding`GO:0071108^biological_process^protein K48-linked deubiquitination	.	.	.	3.883360	4.442863	0.9765421	4.537030	5.705196e-06	0.001111423

gene	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN100127_c0_g1_i1	3.608228	4.480129	1.0997747	4.013424	5.984419e-05	0.007626394
TRINITY_DN101713_c0_g1_i1	9.193390	3.706762	0.8953110	3.997082	6.412797e-05	0.008066841
TRINITY_DN10190_c0_g1_i1	3.596375	3.404744	1.0077576	3.406440	6.581610e-04	0.042200953
TRINITY_DN101_c0_g1_i6	2916.039845	3.000134	0.8203465	3.619463	2.952156e-04	0.023914234
TRINITY_DN101_c0_g4_i1	389.650351	2.999287	0.6984127	4.269612	1.958133e-05	0.003016171
TRINITY_DN10265_c0_g2_i1	3.883360	4.442863	0.9765421	4.537030	5.705196e-06	0.001111423

gene	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN10153_c1_g1_i1	47.303025	-1.928367	0.5315456	-3.618480	2.963379e-04	2.391423e-02
TRINITY_DN1015_c0_g1_i4	23.418584	-6.401983	1.4252019	-3.850651	1.178042e-04	1.255415e-02
TRINITY_DN10186_c1_g1_i1	4.266713	-4.489130	1.2628190	-3.476959	5.071345e-04	3.549361e-02
TRINITY_DN10299_c1_g1_i1	8.938083	-3.546956	0.8856172	-3.855551	1.154693e-04	1.234835e-02
TRINITY_DN103043_c0_g1_i1	73.858175	-6.823159	0.7991789	-8.118936	4.702892e-16	8.461056e-13
TRINITY_DN1040_c0_g1_i5	61.368383	-5.245897	0.6502786	-7.943474	1.965959e-15	3.340493e-12

sample_name	names
<chr>	<chr>
Upper_lip	Sk.10A_fasta90_isoform.counts.tab
Eye	Sk.10B_fasta90_isoform.counts.tab
Gut	Sk.10C_fasta90_isoform.counts.tab
Upper_lip	Sk.6A_fasta90_isoform.counts.tab
Eye	Sk.6B_fasta90_isoform.counts.tab
Gut	Sk.6C_fasta90_isoform..counts.tab
Upper_lip	Sk.7A_fasta90_isoform.counts.tab
Eye	Sk.7B_fasta90_isoform.counts.tab
Gut	Sk.7C_fasta90_isoform.counts.tab
Upper_lip	Sk.8A_fasta90_isoform.counts.tab
Eye	Sk.8B_fasta90_isoform..counts.tab
Gut	Sk.8C_fasta90_isoform..counts.tab
Upper_lip	Sk.9A_fasta90_isoform.counts.tab
Eye	Sk.9B_fasta90_isoform..counts.tab
Gut	Sk.9C_fasta90_isoform.counts.tab

	gene
	<chr>
1	NODE_10126_length_1999_cov_2.60802_g7138_i0
2	NODE_101633_length_138_cov_2.06024_g94413_i0
3	NODE_10232_length_1983_cov_42.0814_g7210_i0
4	NODE_102471_length_136_cov_2.41975_g95251_i0
5	NODE_10387_length_1964_cov_13.2829_g7315_i0
6	NODE_10411_length_1962_cov_1.81279_g354_i2

	Orthogroup
	<chr>
1	OG0000024
2	OG0000025
3	OG0000645
4	OG0000645
5	OG0000044
6	OG0008641

	Orthogroup
	<chr>
1	OG0000094
2	OG0000125
3	OG0003648
4	OG0000094
5	OG0000074
6	OG0005447

	TRINITY_DN0_c0_g1_i2	TRINITY_DN0_c0_g3_i1	TRINITY_DN0_c0_g4_i2	TRINITY_DN100005_c0_g1_i1	TRINITY_DN100010_c0_g1_i1	TRINITY_DN10001_c0_g2_i1	TRINITY_DN10001_c1_g1_i5	TRINITY_DN10002_c0_g2_i1	TRINITY_DN10002_c0_g3_i1	TRINITY_DN10002_c1_g2_i2	⋯	TRINITY_DN9992_c2_g1_i1	TRINITY_DN9993_c0_g1_i1	TRINITY_DN9997_c0_g1_i14	TRINITY_DN9997_c2_g1_i4	TRINITY_DN9998_c0_g1_i1	TRINITY_DN9999_c0_g2_i1	TRINITY_DN999_c0_g1_i5	TRINITY_DN99_c0_g1_i8	TRINITY_DN99_c1_g1_i2	TRINITY_DN9_c0_g1_i1
Sk.10A_fasta90_isoform.counts.tab	-0.4833034	3.513079	2.2217544	3.7108665	-0.4833034	-0.4833034	1.549772	3.0097771	4.424157	5.123181	⋯	-0.4833034	1.5497719	-0.4833034	-0.4833034	4.179557	4.7272979	7.113906	6.595724	-0.4833034	6.409652
Sk.10B_fasta90_isoform.counts.tab	4.2061223	1.286318	5.0482202	2.8977955	1.2863178	-0.4833034	3.887132	-0.4833034	5.379136	5.749601	⋯	-0.4833034	3.7628464	-0.4833034	-0.4833034	4.879275	3.8871317	7.405441	7.840629	2.6371703	7.068321
Sk.10C_fasta90_isoform.counts.tab	8.4121435	5.388425	9.1129710	2.8702510	3.1876272	2.0999435	4.621741	2.9841075	4.786468	4.586408	⋯	3.5239739	4.2673707	4.2673707	3.7327735	4.222018	1.8764900	5.811802	8.119777	4.7864682	3.796123
Sk.6A_fasta90_isoform.counts.tab	-0.4833034	3.088815	3.5962822	-0.4833034	3.4462981	1.8759402	4.512263	1.8759402	4.512263	5.542985	⋯	3.9702006	4.2666132	-0.4833034	-0.4833034	3.446298	-0.4833034	5.983687	6.232227	1.2676680	6.137886
Sk.6B_fasta90_isoform.counts.tab	1.8396698	5.415046	-0.4833034	3.3989581	-0.4833034	-0.4833034	4.734369	2.5674204	3.398958	5.251051	⋯	3.3989581	-0.4833034	-0.4833034	-0.4833034	1.839670	-0.4833034	6.390961	4.734369	2.5674204	3.920894
Sk.6C_fasta90_isoform..counts.tab	8.8222465	6.882231	9.9898509	2.2964139	2.9891895	1.8805966	3.738243	1.8805966	4.911712	5.603886	⋯	4.1323955	4.1808162	4.9952269	4.0822873	4.082287	1.2714137	5.817739	8.107196	5.2657030	4.441411

	transcript_id	colors
	<chr>	<chr>
TRINITY_DN3355_c0_g1_i2	TRINITY_DN3355_c0_g1_i2	antiquewhite2
TRINITY_DN2507_c0_g1_i2	TRINITY_DN2507_c0_g1_i2	antiquewhite4
TRINITY_DN2286_c0_g1_i5	TRINITY_DN2286_c0_g1_i5	bisque4
TRINITY_DN3218_c0_g4_i1	TRINITY_DN3218_c0_g4_i1	bisque4
TRINITY_DN1706_c0_g1_i1	TRINITY_DN1706_c0_g1_i1	brown
TRINITY_DN177_c0_g1_i4	TRINITY_DN177_c0_g1_i4	brown
TRINITY_DN82963_c0_g1_i1	TRINITY_DN82963_c0_g1_i1	brown2
TRINITY_DN16890_c0_g1_i1	TRINITY_DN16890_c0_g1_i1	brown4
TRINITY_DN42_c0_g1_i1	TRINITY_DN42_c0_g1_i1	brown4
TRINITY_DN1749_c0_g1_i2	TRINITY_DN1749_c0_g1_i2	chocolate4
TRINITY_DN696_c0_g1_i1	TRINITY_DN696_c0_g1_i1	chocolate4
TRINITY_DN10898_c0_g2_i5	TRINITY_DN10898_c0_g2_i5	coral4
TRINITY_DN16156_c0_g1_i1	TRINITY_DN16156_c0_g1_i1	coral4
TRINITY_DN21195_c0_g1_i1	TRINITY_DN21195_c0_g1_i1	coral4
TRINITY_DN2400_c0_g1_i1	TRINITY_DN2400_c0_g1_i1	coral4
TRINITY_DN39451_c0_g1_i1	TRINITY_DN39451_c0_g1_i1	coral4
TRINITY_DN42737_c0_g1_i1	TRINITY_DN42737_c0_g1_i1	coral4
TRINITY_DN274_c0_g1_i2	TRINITY_DN274_c0_g1_i2	cyan
TRINITY_DN6920_c0_g1_i1	TRINITY_DN6920_c0_g1_i1	cyan
TRINITY_DN14586_c0_g3_i1	TRINITY_DN14586_c0_g3_i1	darkgrey
TRINITY_DN21940_c0_g1_i2	TRINITY_DN21940_c0_g1_i2	darkgrey
TRINITY_DN27140_c0_g1_i1	TRINITY_DN27140_c0_g1_i1	darkgrey
TRINITY_DN11556_c0_g1_i1	TRINITY_DN11556_c0_g1_i1	darkmagenta
TRINITY_DN16940_c0_g1_i1	TRINITY_DN16940_c0_g1_i1	darkmagenta
TRINITY_DN174_c0_g1_i6	TRINITY_DN174_c0_g1_i6	darkmagenta
TRINITY_DN33065_c0_g1_i1	TRINITY_DN33065_c0_g1_i1	darkmagenta
TRINITY_DN4646_c0_g2_i1	TRINITY_DN4646_c0_g2_i1	darkturquoise
TRINITY_DN908_c0_g2_i1	TRINITY_DN908_c0_g2_i1	darkviolet
TRINITY_DN3729_c0_g1_i3	TRINITY_DN3729_c0_g1_i3	green
TRINITY_DN14703_c0_g1_i6	TRINITY_DN14703_c0_g1_i6	lavenderblush3
TRINITY_DN1778_c0_g1_i2	TRINITY_DN1778_c0_g1_i2	lavenderblush3
TRINITY_DN4229_c0_g2_i1	TRINITY_DN4229_c0_g2_i1	midnightblue
TRINITY_DN565_c0_g1_i1	TRINITY_DN565_c0_g1_i1	midnightblue
TRINITY_DN7244_c4_g1_i1	TRINITY_DN7244_c4_g1_i1	mistyrose
TRINITY_DN41835_c0_g1_i1	TRINITY_DN41835_c0_g1_i1	navajowhite2
TRINITY_DN17668_c0_g1_i1	TRINITY_DN17668_c0_g1_i1	plum1
TRINITY_DN1137_c0_g1_i1	TRINITY_DN1137_c0_g1_i1	tan
TRINITY_DN24066_c0_g1_i1	TRINITY_DN24066_c0_g1_i1	tan
TRINITY_DN11085_c0_g1_i2	TRINITY_DN11085_c0_g1_i2	turquoise
TRINITY_DN1360_c0_g1_i1	TRINITY_DN1360_c0_g1_i1	turquoise
TRINITY_DN3044_c0_g1_i2	TRINITY_DN3044_c0_g1_i2	turquoise
TRINITY_DN3422_c1_g1_i1	TRINITY_DN3422_c1_g1_i1	turquoise
TRINITY_DN3446_c0_g2_i1	TRINITY_DN3446_c0_g2_i1	turquoise
TRINITY_DN4013_c0_g1_i1	TRINITY_DN4013_c0_g1_i1	turquoise
TRINITY_DN51520_c0_g1_i1	TRINITY_DN51520_c0_g1_i1	turquoise
TRINITY_DN671_c0_g1_i1	TRINITY_DN671_c0_g1_i1	turquoise
TRINITY_DN735_c0_g1_i2	TRINITY_DN735_c0_g1_i2	turquoise
TRINITY_DN7748_c0_g1_i4	TRINITY_DN7748_c0_g1_i4	turquoise
TRINITY_DN87164_c0_g1_i1	TRINITY_DN87164_c0_g1_i1	turquoise
TRINITY_DN94583_c0_g1_i1	TRINITY_DN94583_c0_g1_i1	turquoise
TRINITY_DN21901_c0_g1_i1	TRINITY_DN21901_c0_g1_i1	yellow2

Var1	Freq
<fct>	<int>
antiquewhite2	1
antiquewhite4	1
bisque4	2
brown	2
brown2	1
brown4	2
chocolate4	2
coral4	6
cyan	2
darkgrey	3
darkmagenta	4
darkturquoise	1
darkviolet	1
green	1
lavenderblush3	2
midnightblue	2
mistyrose	1
navajowhite2	1
plum1	1
tan	2
turquoise	12
yellow2	1

	skogs
	<chr>
1	TRINITY_DN95414_c0_g1_i1
2	TRINITY_DN15305_c0_g1_i1
3	TRINITY_DN12206_c0_g2_i4
4	TRINITY_DN18899_c0_g1_i1
5	TRINITY_DN70069_c0_g1_i1
6	TRINITY_DN22758_c4_g1_i1

	transcript_id
	<chr>
8	TRINITY_DN9569_c0_g2_i11
10	TRINITY_DN73_c0_g1_i2
11	TRINITY_DN56829_c0_g1_i1
12	TRINITY_DN1643_c0_g1_i1
20	TRINITY_DN56429_c0_g1_i1
26	TRINITY_DN10424_c1_g2_i1

TRINITY_DN14811_c0_g2_i4	TRINITY_DN19387_c0_g1_i1	TRINITY_DN6409_c1_g2_i1	TRINITY_DN3067_c0_g1_i1	TRINITY_DN76446_c0_g1_i1	TRINITY_DN8168_c0_g1_i3	TRINITY_DN7495_c0_g2_i1	TRINITY_DN4926_c0_g1_i1	TRINITY_DN24054_c0_g1_i2	TRINITY_DN346_c0_g1_i10	⋯	TRINITY_DN17668_c0_g1_i1	TRINITY_DN94358_c0_g1_i1	TRINITY_DN4757_c0_g1_i1	TRINITY_DN1277_c0_g1_i1	TRINITY_DN1207_c2_g1_i7	TRINITY_DN6841_c0_g4_i1	TRINITY_DN3697_c0_g1_i1	TRINITY_DN537_c1_g1_i3	TRINITY_DN52483_c0_g1_i1	TRINITY_DN2541_c0_g1_i2
TRINITY_DN18173_c1_g2_i1	TRINITY_DN9475_c0_g2_i3	TRINITY_DN19505_c0_g1_i2	TRINITY_DN871_c1_g1_i1	TRINITY_DN8798_c0_g2_i1	TRINITY_DN49829_c0_g1_i1	TRINITY_DN88612_c0_g1_i1	TRINITY_DN22292_c1_g1_i1	TRINITY_DN2512_c0_g1_i7	TRINITY_DN78344_c0_g1_i1	⋯	TRINITY_DN2560_c0_g1_i6	TRINITY_DN188_c0_g1_i1	TRINITY_DN1091_c5_g1_i1	TRINITY_DN50396_c0_g1_i1	TRINITY_DN3027_c1_g1_i1	TRINITY_DN5552_c0_g3_i1	TRINITY_DN315_c0_g2_i1	TRINITY_DN56244_c0_g1_i1	TRINITY_DN8515_c0_g1_i2	TRINITY_DN18120_c0_g1_i2
TRINITY_DN86044_c0_g1_i1	TRINITY_DN159_c0_g1_i5	TRINITY_DN4882_c0_g1_i2	TRINITY_DN4812_c0_g1_i1	TRINITY_DN668_c1_g1_i1	TRINITY_DN26170_c0_g1_i2	TRINITY_DN3586_c0_g1_i2	TRINITY_DN17231_c0_g1_i1	TRINITY_DN6806_c1_g1_i4	TRINITY_DN2343_c0_g1_i1	⋯	TRINITY_DN14205_c0_g2_i4	TRINITY_DN5257_c0_g2_i3	TRINITY_DN2285_c0_g1_i1	TRINITY_DN9573_c0_g4_i1	TRINITY_DN4926_c0_g1_i1	TRINITY_DN4573_c0_g1_i2	TRINITY_DN2373_c0_g1_i1	TRINITY_DN88412_c0_g1_i1	TRINITY_DN2368_c0_g3_i1	TRINITY_DN34621_c0_g1_i1
TRINITY_DN3089_c1_g1_i2	TRINITY_DN18054_c0_g3_i2	TRINITY_DN33258_c0_g1_i1	TRINITY_DN26828_c0_g1_i1	TRINITY_DN21370_c0_g1_i1	TRINITY_DN87_c0_g3_i1	TRINITY_DN76_c0_g1_i1	TRINITY_DN4438_c0_g1_i10	TRINITY_DN5476_c0_g1_i6	TRINITY_DN19694_c0_g1_i2	⋯	TRINITY_DN13695_c0_g1_i2	TRINITY_DN7495_c0_g2_i1	TRINITY_DN21117_c0_g1_i1	TRINITY_DN2115_c0_g1_i2	TRINITY_DN21213_c0_g1_i1	TRINITY_DN5832_c0_g1_i1	TRINITY_DN42008_c0_g1_i1	TRINITY_DN13849_c0_g1_i1	TRINITY_DN7202_c0_g1_i1	TRINITY_DN3586_c1_g3_i2
TRINITY_DN28789_c0_g1_i3	TRINITY_DN10639_c2_g1_i1	TRINITY_DN19170_c0_g1_i1	TRINITY_DN20601_c0_g1_i1	TRINITY_DN14161_c0_g1_i2	TRINITY_DN5116_c1_g1_i1	TRINITY_DN2782_c0_g1_i1	TRINITY_DN20555_c0_g1_i1	TRINITY_DN10190_c1_g1_i4	TRINITY_DN278_c1_g1_i2	⋯	TRINITY_DN12950_c0_g1_i6	TRINITY_DN23452_c0_g1_i2	TRINITY_DN77121_c0_g1_i1	TRINITY_DN2368_c0_g3_i1	TRINITY_DN10814_c0_g1_i1	TRINITY_DN10_c1_g1_i1	TRINITY_DN77125_c0_g1_i1	TRINITY_DN97832_c0_g1_i1	TRINITY_DN33303_c0_g1_i2	TRINITY_DN31990_c0_g1_i1
TRINITY_DN4794_c0_g1_i1	TRINITY_DN15266_c0_g1_i1	TRINITY_DN2511_c0_g1_i5	TRINITY_DN16744_c0_g2_i3	TRINITY_DN76032_c0_g1_i1	TRINITY_DN12545_c1_g1_i1	TRINITY_DN5892_c3_g1_i1	TRINITY_DN9583_c0_g1_i2	TRINITY_DN33980_c0_g1_i1	TRINITY_DN2866_c0_g1_i1	⋯	TRINITY_DN76169_c0_g1_i1	TRINITY_DN10600_c0_g1_i1	TRINITY_DN13_c0_g1_i1	TRINITY_DN10688_c0_g2_i6	TRINITY_DN55_c0_g1_i1	TRINITY_DN41839_c0_g1_i3	TRINITY_DN3974_c0_g1_i1	TRINITY_DN1410_c0_g1_i1	TRINITY_DN6713_c1_g1_i3	TRINITY_DN13830_c0_g1_i1

A data.table: 6 × 23
#gene_id	transcript_id	sprot_Top_BLASTX_hit	RNAMMER	prot_id	prot_coords	sprot_Top_BLASTP_hit	Pfam	SignalP	TmHMM	⋯	gene_ontology_BLASTP	gene_ontology_Pfam	transcript	peptide	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	⋯	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN0_c0_g1	TRINITY_DN0_c0_g1_i2	CPVL_MOUSE^CPVL_MOUSE^Q:2582-1206,H:3-471^44.186%ID^E:2.53e-133^RecName: Full=Probable serine carboxypeptidase CPVL;^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia; Eutheria; Euarchontoglires; Glires; Rodentia; Myomorpha; Muroidea; Muridae; Murinae; Mus; Mus	.	TRINITY_DN0_c0_g1_i2.p1	1194-2573[-]	CPVL_MOUSE^CPVL_MOUSE^Q:2-456,H:7-471^44.35%ID^E:3.55e-138^RecName: Full=Probable serine carboxypeptidase CPVL;^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia; Eutheria; Euarchontoglires; Glires; Rodentia; Myomorpha; Muroidea; Muridae; Murinae; Mus; Mus	PF00450.25^Peptidase_S10^Serine carboxypeptidase^67-454^E:2.7e-98	sigP:1^17^0.818	.	⋯	GO:0004185^molecular_function^serine-type carboxypeptidase activity	GO:0004185^molecular_function^serine-type carboxypeptidase activity`GO:0006508^biological_process^proteolysis	.	.	87.728134	4.116102	0.7598392	5.379869	7.454017e-08	4.057540e-06
TRINITY_DN0_c0_g4	TRINITY_DN0_c0_g4_i2	VCP_APIME^VCP_APIME^Q:1935-634,H:24-463^44.743%ID^E:1.97e-118^RecName: Full=Venom serine carboxypeptidase;^Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota; Neoptera; Endopterygota; Hymenoptera; Apocrita; Aculeata; Apoidea; Apidae; Apis	.	TRINITY_DN0_c0_g4_i2.p1	619-2025[-]	VCP_APIME^VCP_APIME^Q:6-463,H:3-462^43.856%ID^E:1.3e-122^RecName: Full=Venom serine carboxypeptidase;^Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota; Neoptera; Endopterygota; Hymenoptera; Apocrita; Aculeata; Apoidea; Apidae; Apis	PF00450.25^Peptidase_S10^Serine carboxypeptidase^75-465^E:5.3e-92	sigP:1^19^0.803	.	⋯	GO:0005576^cellular_component^extracellular region`GO:0004185^molecular_function^serine-type carboxypeptidase activity	GO:0004185^molecular_function^serine-type carboxypeptidase activity`GO:0006508^biological_process^proteolysis	.	.	223.765662	2.713450	0.8205288	3.292472	9.931093e-04	1.222380e-02
TRINITY_DN10004_c4_g1	TRINITY_DN10004_c4_g1_i1	.	.	.	.	.	.	.	.	⋯	.	.	.	.	1.799057	3.472197	1.0458778	3.299393	9.689408e-04	1.200249e-02
TRINITY_DN10008_c0_g1	TRINITY_DN10008_c0_g1_i1	ENDUB_DANRE^ENDUB_DANRE^Q:1009-266,H:7-282^28.261%ID^E:1.58e-20^RecName: Full=Uridylate-specific endoribonuclease B {ECO:0000305};^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Actinopterygii; Neopterygii; Teleostei; Ostariophysi; Cypriniformes; Danionidae; Danioninae; Danio	.	TRINITY_DN10008_c0_g1_i1.p1	179-1096[-]	ENDUB_DANRE^ENDUB_DANRE^Q:24-277,H:1-282^28.723%ID^E:1.04e-24^RecName: Full=Uridylate-specific endoribonuclease B {ECO:0000305};^Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Actinopterygii; Neopterygii; Teleostei; Ostariophysi; Cypriniformes; Danionidae; Danioninae; Danio	PF09412.13^XendoU^Endoribonuclease XendoU^31-274^E:6.7e-45	sigP:1^21^0.779	.	⋯	GO:0004521^molecular_function^endoribonuclease activity`GO:0016829^molecular_function^lyase activity`GO:0046872^molecular_function^metal ion binding`GO:0003723^molecular_function^RNA binding	GO:0004521^molecular_function^endoribonuclease activity	.	.	8.605574	4.926932	1.2519127	3.917817	8.935435e-05	1.798068e-03
TRINITY_DN100098_c0_g1	TRINITY_DN100098_c0_g1_i1	.	.	.	.	.	.	.	.	⋯	.	.	.	.	17.835682	7.063379	0.9234800	7.363776	1.787794e-13	3.867227e-11
TRINITY_DN1000_c1_g1	TRINITY_DN1000_c1_g1_i2	.	.	.	.	.	.	.	.	⋯	.	.	.	.	134.170410	1.370024	0.3804016	3.600218	3.179503e-04	4.979644e-03

A tibble: 6 × 7
gene	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN0_c0_g1_i2	87.728134	4.116102	0.7598392	5.379869	7.454017e-08	4.057540e-06
TRINITY_DN0_c0_g4_i2	223.765662	2.713450	0.8205288	3.292472	9.931093e-04	1.222380e-02
TRINITY_DN10004_c4_g1_i1	1.799057	3.472197	1.0458778	3.299393	9.689408e-04	1.200249e-02
TRINITY_DN10008_c0_g1_i1	8.605574	4.926932	1.2519127	3.917817	8.935435e-05	1.798068e-03
TRINITY_DN100098_c0_g1_i1	17.835682	7.063379	0.9234800	7.363776	1.787794e-13	3.867227e-11
TRINITY_DN1000_c1_g1_i2	134.170410	1.370024	0.3804016	3.600218	3.179503e-04	4.979644e-03

A tibble: 6 × 7
gene	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN10002_c1_g1_i1	2.520034	-3.373872	1.1281647	-2.896979	3.767749e-03	3.257075e-02
TRINITY_DN10016_c3_g1_i2	46.654265	-2.021507	0.5571204	-3.628127	2.854847e-04	4.588174e-03
TRINITY_DN10036_c0_g1_i1	12.458310	-2.076170	0.6114870	-3.390928	6.965633e-04	9.174321e-03
TRINITY_DN10044_c1_g1_i1	2.893933	-3.509221	1.0126332	-3.316095	9.128492e-04	1.143451e-02
TRINITY_DN1004_c0_g1_i5	793.893694	-3.975748	0.7871186	-5.073644	3.902699e-07	1.732798e-05
TRINITY_DN10062_c0_g1_i1	9.145714	-3.762179	1.0732028	-3.471206	5.181254e-04	7.298007e-03

A tibble: 6 × 7
gene	baseMean	log2FoldChange	lfcSE	stat	pvalue	padj
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
TRINITY_DN100127_c0_g1_i1	3.608228	2.729312	0.9341722	2.880301	3.972962e-03	3.335116e-02
TRINITY_DN10016_c3_g1_i2	46.654265	2.277662	0.5551594	4.102007	4.095821e-05	8.875274e-04
TRINITY_DN10031_c3_g1_i1	16.544037	1.833604	0.3699002	4.954538	7.250222e-07	3.064050e-05
TRINITY_DN100493_c0_g1_i1	4.249253	3.571458	1.1454913	3.046927	2.311939e-03	2.223371e-02
TRINITY_DN1004_c0_g1_i5	793.893694	5.194943	0.7868477	6.614398	3.730678e-11	5.611549e-09
TRINITY_DN10062_c0_g1_i1	9.145714	3.531921	1.0737770	3.268208	1.082309e-03	1.250321e-02

Table of Contents

Load libraries

Load data

QC for downstream analyses

Barplot of counts for all samples

Visualize transformed expression matrix with hierarchical clustering and PCA

Import the annotation for Skogsbergia sp. transcriptome

Prep expression matrix for WGCNA

Differential gene expression

DGE - Upper Lip vs Compound Eye

DGE - Gut vs Compound Eye

DGE - Upper Lip vs Gut

Determine tissue-specific expression

Upper lip

Compound eye

Gut

Venn Diagram - Extract tissue-specific genes

Identify the number of shared significantly upregulated genes between tissue types across V.tsujii and Skogsbergia sp.

Determine the number of shared significantly upregulated genes between compound eyes

Import

Determine the orthogroups that contain V.tsujii significantly upregulated compound eye genes

Determine the orthogroups that contain Skogsbergia sp. significantly upregulated compound eye genes

Determine the number of orthogroups with significantly upregulated compound eye genes shared between V.tsujii and Skogsbergia sp.

Extract all V.tsujii significantly upregulated compound eye genes from orthogroups shared across both compound eyes

Extract all Skogsbergia sp. significantly upregulated genes from orthogroups shared across both compound eyes

Determine the number of shared significantly upregulated genes between luminous upper lip and non-lumunous upper lip

Import

Determine the orthogroups that contain V.tsujii significantly upregulated bioluminescent upper lip genes

Determine the orthogroups that have Skogsbergia sp. significantly upregulated upper lip genes

Determine the number of orthogroups with significantly upregulated genes shared between luminous upper lip and non-luminous upper lip.

Extract all V.tsujii significantly upregulated bioluminescent upper lip genes from orthogroups shared across both upper lips

Extract all Skogsbergia sp. significantly upregulated bioluminescent upper lip genes from orthogroups shared across both upper lips

DGE - GO enrichment analyses for upper lip

Use topGO to identify enriched biological processes in the upper lip

Use topGO to identify enriched molecular functions in the upper lip

WGCNA

Run WGCNA

Module to trait heatmap

WGCNA Function

Determine the number of Skogsbergia sp. networks that contain BCN one-to-one orthologs

Module info

Determine if BCN one-to-one orthologs are conserved in Skogsbergia sp. networks

References